Emotion is Not Just a Label: Latent Emotional Factors in LLM Processing

• URL: http://arxiv.org/abs/2603.09205v2
• Date: Mon, 16 Mar 2026 17:52:20 GMT
• Title: Emotion is Not Just a Label: Latent Emotional Factors in LLM Processing
• Abstract summary: We study emotion as a latent factor that shapes how models attend to and reason over text.<n>We analyze how emotional tone systematically alters attention geometry in transformer models.<n>We propose an emotional regularization framework that constrains emotion-conditioned representational drift during training.
• Score: 4.733799057798266
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models are routinely deployed on text that varies widely in emotional tone, yet their reasoning behavior is typically evaluated without accounting for emotion as a source of representational variation. Prior work has largely treated emotion as a prediction target, for example in sentiment analysis or emotion classification. In contrast, we study emotion as a latent factor that shapes how models attend to and reason over text. We analyze how emotional tone systematically alters attention geometry in transformer models, showing that metrics such as locality, center-of-mass distance, and entropy vary across emotions and correlate with downstream question-answering performance. To facilitate controlled study of these effects, we introduce Affect-Uniform ReAding QA (AURA-QA), a question-answering dataset with emotionally balanced, human-authored context passages. Finally, an emotional regularization framework is proposed that constrains emotion-conditioned representational drift during training. Experiments across multiple QA benchmarks demonstrate that this approach improves reading comprehension in both emotionally-varying and non-emotionally varying datasets, yielding consistent gains under distribution shift and in-domain improvements on several benchmarks.

Related papers

• Do Emotions in Prompts Matter? Effects of Emotional Framing on Large Language Models [5.079126066502806]
  Emotional tone is pervasive in human communication, yet its influence on large language model (LLM) behaviour remains unclear.<n>Here, we examine how first-person emotional framing in user-side queries affect LLM performance across six benchmark domains.<n>We introduce EmotionRL, an adaptive emotional prompting framework that selects emotional framing adaptively for each query.
  arXiv  Detail & Related papers  (2026-04-02T16:31:08Z)
• Emotion Entanglement and Bayesian Inference for Multi-Dimensional Emotion Understanding [40.766332191425]
  EmoScene is a theory-grounded benchmark of 4,731 context-rich scenarios annotated with an 8-dimensional emotion vector.<n>We propose an entanglement-aware Bayesian inference framework that incorporates emotion co-occurrence statistics to perform joint posterior inference over the emotion vector.
  arXiv  Detail & Related papers  (2026-04-01T12:27:04Z)
• FACE-net: Factual Calibration and Emotion Augmentation for Retrieval-enhanced Emotional Video Captioning [81.33341786837974]
  Emotional Video Captioning (EVC) is an emerging task, which aims to describe factual content with the intrinsic emotions expressed in videos.<n>We propose a retrieval-enhanced framework with FActual and Emotion augmentation (FACE-net)<n>FACE-net collaboratively mines factual-emotional semantics and provides adaptive and accurate guidance for generation.
  arXiv  Detail & Related papers  (2026-03-18T07:53:15Z)
• Detecting Emotional Dynamic Trajectories: An Evaluation Framework for Emotional Support in Language Models [6.810484095299127]
  Emotional support is a core capability in human-AI interaction, with applications including psychological counseling, role play, and companionship.<n>Existing evaluations of large language models (LLMs) often rely on short, static dialogues and fail to capture the dynamic and long-term nature of emotional support.<n>Our framework constructs a large-scale benchmark consisting of 328 emotional contexts and 1,152 disturbance events, simulating realistic emotional shifts under evolving dialogue scenarios.
  arXiv  Detail & Related papers  (2025-11-12T05:47:28Z)
• Fine-Grained Emotion Recognition via In-Context Learning [24.79387634284384]
  Fine-grained emotion recognition aims to identify the emotional type in queries through reasoning and decision-making processes.<n>Recent methods use In-Context Learning (ICL), enhancing the representation of queries through semantically similar examples.<n>This paper investigates decision-making in fine-grained emotion recognition through prototype theory.
  arXiv  Detail & Related papers  (2025-10-08T03:17:09Z)
• Mechanistic Interpretability of Emotion Inference in Large Language Models [16.42503362001602]
  We show that emotion representations are functionally localized to specific regions in large language models.<n>We draw on cognitive appraisal theory to show that emotions emerge from evaluations of environmental stimuli.<n>This work highlights a novel way to causally intervene and precisely shape emotional text generation.
  arXiv  Detail & Related papers  (2025-02-08T08:11:37Z)
• Improved Text Emotion Prediction Using Combined Valence and Arousal Ordinal Classification [37.823815777259036]
  We introduce a method for categorizing emotions from text, which acknowledges and differentiates between the diversified similarities and distinctions of various emotions. Our approach not only preserves high accuracy in emotion prediction but also significantly reduces the magnitude of errors in cases of misclassification.
  arXiv  Detail & Related papers  (2024-04-02T10:06:30Z)
• Enhancing Emotional Generation Capability of Large Language Models via Emotional Chain-of-Thought [50.13429055093534]
  Large Language Models (LLMs) have shown remarkable performance in various emotion recognition tasks. We propose the Emotional Chain-of-Thought (ECoT) to enhance the performance of LLMs on various emotional generation tasks.
  arXiv  Detail & Related papers  (2024-01-12T16:42:10Z)
• Language Models (Mostly) Do Not Consider Emotion Triggers When Predicting Emotion [87.18073195745914]
  We investigate how well human-annotated emotion triggers correlate with features deemed salient in their prediction of emotions. Using EmoTrigger, we evaluate the ability of large language models to identify emotion triggers. Our analysis reveals that emotion triggers are largely not considered salient features for emotion prediction models, instead there is intricate interplay between various features and the task of emotion detection.
  arXiv  Detail & Related papers  (2023-11-16T06:20:13Z)
• Implicit Design Choices and Their Impact on Emotion Recognition Model Development and Evaluation [5.534160116442057]
  The subjectivity of emotions poses significant challenges in developing accurate and robust computational models. This thesis examines critical facets of emotion recognition, beginning with the collection of diverse datasets. To handle the challenge of non-representative training data, this work collects the Multimodal Stressed Emotion dataset.
  arXiv  Detail & Related papers  (2023-09-06T02:45:42Z)
• Seeking Subjectivity in Visual Emotion Distribution Learning [93.96205258496697]
  Visual Emotion Analysis (VEA) aims to predict people's emotions towards different visual stimuli. Existing methods often predict visual emotion distribution in a unified network, neglecting the inherent subjectivity in its crowd voting process. We propose a novel textitSubjectivity Appraise-and-Match Network (SAMNet) to investigate the subjectivity in visual emotion distribution.
  arXiv  Detail & Related papers  (2022-07-25T02:20:03Z)
• Emotion Recognition from Multiple Modalities: Fundamentals and Methodologies [106.62835060095532]
  We discuss several key aspects of multi-modal emotion recognition (MER) We begin with a brief introduction on widely used emotion representation models and affective modalities. We then summarize existing emotion annotation strategies and corresponding computational tasks. Finally, we outline several real-world applications and discuss some future directions.
  arXiv  Detail & Related papers  (2021-08-18T21:55:20Z)
• A Circular-Structured Representation for Visual Emotion Distribution Learning [82.89776298753661]
  We propose a well-grounded circular-structured representation to utilize the prior knowledge for visual emotion distribution learning. To be specific, we first construct an Emotion Circle to unify any emotional state within it. On the proposed Emotion Circle, each emotion distribution is represented with an emotion vector, which is defined with three attributes.
  arXiv  Detail & Related papers  (2021-06-23T14:53:27Z)
• Enhancing Cognitive Models of Emotions with Representation Learning [58.2386408470585]
  We present a novel deep learning-based framework to generate embedding representations of fine-grained emotions. Our framework integrates a contextualized embedding encoder with a multi-head probing model. Our model is evaluated on the Empathetic Dialogue dataset and shows the state-of-the-art result for classifying 32 emotions.
  arXiv  Detail & Related papers  (2021-04-20T16:55:15Z)
• Modality-Transferable Emotion Embeddings for Low-Resource Multimodal Emotion Recognition [55.44502358463217]
  We propose a modality-transferable model with emotion embeddings to tackle the aforementioned issues. Our model achieves state-of-the-art performance on most of the emotion categories. Our model also outperforms existing baselines in the zero-shot and few-shot scenarios for unseen emotions.
  arXiv  Detail & Related papers  (2020-09-21T06:10:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.