Are Emotions Arranged in a Circle? Geometric Analysis of Emotion Representations via Hyperspherical Contrastive Learning

• URL: http://arxiv.org/abs/2601.06575v2
• Date: Tue, 13 Jan 2026 03:30:23 GMT
• Title: Are Emotions Arranged in a Circle? Geometric Analysis of Emotion Representations via Hyperspherical Contrastive Learning
• Abstract summary: This paper proposes a method to induce circular emotion representations within language model embeddings via contrastive learning on a hypersphere.<n>We show that while this circular alignment offers superior interpretability and robustness against dimensionality reduction, it underperforms compared to conventional designs in high-dimensional settings and fine-grained classification.
• Score: 18.807120508172407
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Psychological research has long utilized circumplex models to structure emotions, placing similar emotions adjacently and opposing ones diagonally. Although frequently used to interpret deep learning representations, these models are rarely directly incorporated into the representation learning of language models, leaving their geometric validity unexplored. This paper proposes a method to induce circular emotion representations within language model embeddings via contrastive learning on a hypersphere. We show that while this circular alignment offers superior interpretability and robustness against dimensionality reduction, it underperforms compared to conventional designs in high-dimensional settings and fine-grained classification. Our findings elucidate the trade-offs involved in applying psychological circumplex models to deep learning architectures.

Related papers

• Busemann energy-based attention for emotion analysis in Poincaré discs [0.0]
  EmBolic is a novel fully hyperbolic deep learning architecture for fine-grained emotion analysis from textual messages.<n>EmBolic aims to infer the curvature on the continuous space of emotions, rather than treating them as a categorical set without any metric structure.<n>Our experiments demonstrate strong generalization properties and reasonably good prediction accuracy even for small dimensions of the representation space.
  arXiv  Detail & Related papers  (2026-04-08T07:19:52Z)
• Latent Structure of Affective Representations in Large Language Models [6.345340156849189]
  We investigate the latent structure of affective representations in large language models (LLMs) using geometric data analysis tools.<n>First, we show that LLMs learn coherent latent representations of affective emotions that align with widely used valence--arousal models from psychology.<n>Second, we find that these representations exhibit nonlinear geometric structure that can nonetheless be well-approximated linearly.<n>Third, we demonstrate that the learned latent representation space can be leveraged to quantify uncertainty in emotion processing tasks.
  arXiv  Detail & Related papers  (2026-04-08T02:13:48Z)
• Emotions Where Art Thou: Understanding and Characterizing the Emotional Latent Space of Large Language Models [5.171335396838995]
  This work investigates how large language models (LLMs) internally represent emotion by analyzing the geometry of their hidden-state space.<n>The paper identifies a low-dimensional emotional manifold and shows that emotional representations are directionally encoded, distributed across layers, and aligned with interpretable dimensions.
  arXiv  Detail & Related papers  (2025-10-24T21:54:12Z)
• 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)
• Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling [50.99252242917458]
  Conversational Speech Synthesis (CSS) aims to accurately express an utterance with the appropriate prosody and emotional inflection within a conversational setting. To address the issue of data scarcity, we meticulously create emotional labels in terms of category and intensity. Our model outperforms the baseline models in understanding and rendering emotions.
  arXiv  Detail & Related papers  (2023-12-19T08:47:50Z)
• StyleEDL: Style-Guided High-order Attention Network for Image Emotion Distribution Learning [69.06749934902464]
  We propose a style-guided high-order attention network for image emotion distribution learning termed StyleEDL. StyleEDL interactively learns stylistic-aware representations of images by exploring the hierarchical stylistic information of visual contents. In addition, we introduce a stylistic graph convolutional network to dynamically generate the content-dependent emotion representations.
  arXiv  Detail & Related papers  (2023-08-06T03:22:46Z)
• Semi-supervised learning for continuous emotional intensity controllable speech synthesis with disentangled representations [16.524515747017787]
  We propose a novel method to control the continuous intensity of emotions using semi-supervised learning. The experimental results showed that the proposed method was superior in controllability and naturalness.
  arXiv  Detail & Related papers  (2022-11-11T12:28:07Z)
• Contrast and Generation Make BART a Good Dialogue Emotion Recognizer [38.18867570050835]
  Long-range contextual emotional relationships with speaker dependency play a crucial part in dialogue emotion recognition. We adopt supervised contrastive learning to make different emotions mutually exclusive to identify similar emotions better. We utilize an auxiliary response generation task to enhance the model's ability of handling context information.
  arXiv  Detail & Related papers  (2021-12-21T13:38:00Z)
• 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)
• Quadric hypersurface intersection for manifold learning in feature space [52.83976795260532]
  manifold learning technique suitable for moderately high dimension and large datasets. The technique is learned from the training data in the form of an intersection of quadric hypersurfaces. At test time, this manifold can be used to introduce an outlier score for arbitrary new points.
  arXiv  Detail & Related papers  (2021-02-11T18:52:08Z)
• Facial Expression Editing with Continuous Emotion Labels [76.36392210528105]
  Deep generative models have achieved impressive results in the field of automated facial expression editing. We propose a model that can be used to manipulate facial expressions in facial images according to continuous two-dimensional emotion labels.
  arXiv  Detail & Related papers  (2020-06-22T13:03:02Z)

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.