Mechanistic Decoding of Cognitive Constructs in Large Language Models

• URL: http://arxiv.org/abs/2604.14593v3
• Date: Wed, 22 Apr 2026 09:12:17 GMT
• Title: Mechanistic Decoding of Cognitive Constructs in Large Language Models
• Abstract summary: We propose a Cognitive Reverse-Engineering framework based on Representation Engineering to analyze social-comparison jealousy.<n>By combining appraisal theory with subspaceization, regression-based weighting, and bidirectional causal steering, we isolate and quantify two psychological antecedents of jealousy.<n>Our framework also demonstrates that toxic emotional states can be mechanically detected and surgically suppressed, suggesting a possible route toward representational monitoring and intervention for AI safety in multi-agent environments.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While Large Language Models (LLMs) demonstrate increasingly sophisticated affective capabilities, the internal mechanisms by which they process complex emotions remain unclear. Existing interpretability approaches often treat models as black boxes or focus on coarse-grained basic emotions, leaving the cognitive structure of more complex affective states underexplored. To bridge this gap, we propose a Cognitive Reverse-Engineering framework based on Representation Engineering (RepE) to analyze social-comparison jealousy. By combining appraisal theory with subspace orthogonalization, regression-based weighting, and bidirectional causal steering, we isolate and quantify two psychological antecedents of jealousy, Superiority of Comparison Person and Domain Self-Definitional Relevance, and examine their causal effects on model judgments. Experiments on eight LLMs from the Llama, Qwen, and Gemma families suggest that models natively encode jealousy as a structured linear combination of these constituent factors. Their internal representations are broadly consistent with the human psychological construct, treating Superiority as the foundational trigger and Relevance as the ultimate intensity multiplier. Our framework also demonstrates that toxic emotional states can be mechanically detected and surgically suppressed, suggesting a possible route toward representational monitoring and intervention for AI safety in multi-agent environments.

Related papers

• NeuroCogMap Reveals Cognitive Organization of Large Language Models [82.70079471723963]
  We present NeuroCogMap, a cognitive neuroscience-inspired framework that organizes internal features of large language models into functional parcels.<n>These parcels form a stable and semantically coherent organization that is partly conserved across models.<n>These findings establish NeuroCogMap as a system-level framework for mapping functional organization in artificial systems.
  arXiv  Detail & Related papers  (2026-07-01T03:48:49Z)
• Uneven Evolution of Cognition Across Generations of Generative AI Models [13.772329509422201]
  The pursuit of artificial general intelligence requires robust methods for evaluating the cognitive capabilities of models beyond narrow task performance.<n>Here, we introduce a psychometric framework to assess the cognitive profiles of generative AI, comparing them to human norms and tracking their evolution across generations.
  arXiv  Detail & Related papers  (2026-05-07T18:16:49Z)
• A Survey of Reasoning in Autonomous Driving Systems: Open Challenges and Emerging Paradigms [49.66022971508878]
  We argue that reasoning should be elevated from a modular component to the system's cognitive core.<n>We derive and systematize seven core reasoning challenges, such as the responsiveness-reasoning trade-off and social-game reasoning.<n>We identify a fundamental and unresolved tension between the high-latency, deliberative nature of LLM-based reasoning and the millisecond-scale, safety-critical demands of vehicle control.
  arXiv  Detail & Related papers  (2026-03-11T07:40:53Z)
• Memory-guided Prototypical Co-occurrence Learning for Mixed Emotion Recognition [56.00118641432005]
  We propose a Memory-guided Prototypical Co-occurrence Learning framework that explicitly models emotion co-occurrence patterns.<n>Inspired by human cognitive memory systems, we introduce a memory retrieval strategy to extract semantic-level co-occurrence associations.<n>Our model learns affectively informative representations for accurate emotion distribution prediction.
  arXiv  Detail & Related papers  (2026-02-24T04:11:25Z)
• HUMANLLM: Benchmarking and Reinforcing LLM Anthropomorphism via Human Cognitive Patterns [59.17423586203706]
  We present HUMANLLM, a framework treating psychological patterns as interacting causal forces.<n>We construct 244 patterns from 12,000 academic papers and synthesize 11,359 scenarios where 2-5 patterns reinforce, conflict, or modulate each other.<n>Our dual-level checklists evaluate both individual pattern fidelity and emergent multi-pattern dynamics, achieving strong human alignment.
  arXiv  Detail & Related papers  (2026-01-15T08:56:53Z)
• E^2-LLM: Bridging Neural Signals and Interpretable Affective Analysis [54.763420895859035]
  We present ELLM2-EEG-to-Emotion Large Language Model, first MLLM framework for interpretable emotion analysis from EEG.<n>ELLM integrates a pretrained EEG encoder with Q-based LLMs through learnable projection layers, employing a multi-stage training pipeline.<n>Experiments on the dataset across seven emotion categories demonstrate that ELLM2-EEG-to-Emotion Large Language Model achieves excellent performance on emotion classification.
  arXiv  Detail & Related papers  (2026-01-11T13:21:20Z)
• Cognitive Foundations for Reasoning and Their Manifestation in LLMs [63.12951576410617]
  Large language models (LLMs) solve complex problems yet fail on simpler variants, suggesting they achieve correct outputs through mechanisms fundamentally different from human reasoning.<n>We synthesize cognitive science research into a taxonomy of 28 cognitive elements spanning reasoning invariants, meta-cognitive controls, representations for organizing reasoning & knowledge, and transformation operations.<n>We develop test-time reasoning guidance that automatically scaffold successful structures, improving performance by up to 66.7% on complex problems.
  arXiv  Detail & Related papers  (2025-11-20T18:59:00Z)
• Automatic Minds: Cognitive Parallels Between Hypnotic States and Large Language Model Processing [0.0]
  The cognitive processes of the hypnotized mind and the computational operations of large language models share deep functional parallels.<n>Both systems generate sophisticated, contextually appropriate behavior through automatic pattern-completion mechanisms.<n>The future of reliable AI lies in hybrid architectures that integrate generative fluency with mechanisms of executive monitoring.
  arXiv  Detail & Related papers  (2025-11-03T09:08:50Z)
• AgentZero++: Modeling Fear-Based Behavior [4.783433971864009]
  We present AgentZero++, an agent-based model that integrates cognitive, emotional, and social mechanisms to simulate collective violence.<n>Building on Epstein's Agent_Zero framework, we extend the original model with eight behavioral enhancements.<n>These additions allow agents to adapt based on internal states, previous experiences, and social feedback.
  arXiv  Detail & Related papers  (2025-10-05T22:33:56Z)
• LLM Assertiveness can be Mechanistically Decomposed into Emotional and Logical Components [0.17188280334580197]
  Large Language Models (LLMs) often display overconfidence, presenting information with unwarranted certainty in high-stakes contexts.<n>We use open-sourced Llama 3.2 models fine-tuned on human annotated assertiveness datasets.<n>Our analysis identifies layers most sensitive to assertiveness contrasts and reveals that high-assertive representations decompose into two sub-components of emotional and logical clusters.
  arXiv  Detail & Related papers  (2025-08-24T01:43:48Z)
• Failure Modes of LLMs for Causal Reasoning on Narratives [51.19592551510628]
  We investigate the interaction between world knowledge and logical reasoning.<n>We find that state-of-the-art large language models (LLMs) often rely on superficial generalizations.<n>We show that simple reformulations of the task can elicit more robust reasoning behavior.
  arXiv  Detail & Related papers  (2024-10-31T12:48:58Z)
• A Hierarchical Regression Chain Framework for Affective Vocal Burst Recognition [72.36055502078193]
  We propose a hierarchical framework, based on chain regression models, for affective recognition from vocal bursts. To address the challenge of data sparsity, we also use self-supervised learning (SSL) representations with layer-wise and temporal aggregation modules. The proposed systems participated in the ACII Affective Vocal Burst (A-VB) Challenge 2022 and ranked first in the "TWO'' and "CULTURE" tasks.
  arXiv  Detail & Related papers  (2023-03-14T16:08:45Z)

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.