mlsanityData to 7 Oct 2026

How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study

arXiv 2604.00005 ↗First posted 9 Mar 2026cs.AI cs.CLcited by 1

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

Emotion plays an important role in human cognition and performance. Motivated by this, we investigate whether analogous emotional signals can shape the behavior of large language models (LLMs) and agents. Existing emotion-aware studies mainly treat emotion as a surface-level style factor or a perception target, overlooking its mechanistic role in task processing. To address this limitation, we propose E-STEER, an interpretable emotion steering framework that enables direct representation-level intervention in LLMs and agents. It embeds emotion as a structured, controllable variable in hidden states, and with it, we examine the impact of emotion on objective reasoning, subjective generation, safety, and multi-step agent behaviors. The results reveal non-monotonic emotion-behavior relations consistent with established psychological theories, and show that specific emotions not only enhance LLM capability but also improve safety, and systematically shape multi-step agent behaviors.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 25 of its 43 references that are in the map. First posted on arXiv 9 Mar 2026.

Builds on

25 of 43 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026Controlling Long-Horizon Behavior in Language Model Agents with Explicit State Dynamics22 Jan
  2. 2025EvoEmo: Towards Evolved Emotional Policies for Adversarial LLM Agents in Multi-Turn Price Negotiation4 Sep

Other references · 23

  1. 2025Qwen3 Technical Reportcited by 8,195
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  4. 2021Program Synthesis with Large Language Modelscited by 3,509
  5. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  6. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,330
  7. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,258
  8. 2018Hierarchical Neural Story Generationcited by 1,182
  9. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  10. 2024Large Language Models: A Surveycited by 506
  11. 2024JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Modelscited by 494
  12. 2023TinyStories: How Small Can Language Models Be and Still Speak Coherent English?cited by 425
11 more
  1. 2025Persona Vectors: Monitoring and Controlling Character Traits in Language Modelscited by 303
  2. 2020LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoningcited by 68
  3. 2025PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Modelscited by 57
  4. 2025NRC VAD Lexicon v2: Norms for Valence, Arousal, and Dominance for over 55k English Termscited by 25
  5. 2025Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agentscited by 20
  6. 2025Emotions Where Art Thou: Understanding and Characterizing the Emotional Latent Space of Large Language Modelscited by 14
  7. 2024Cause-Aware Empathetic Response Generation via Chain-of-Thought Fine-Tuningcited by 11
  8. 2025Decoding Emotion in the Deep: A Systematic Study of How LLMs Represent, Retain, and Express Emotioncited by 10
  9. 2019EmotionX-HSU: Adopting Pre-trained BERT for Emotion Classificationcited by 2
  10. 2025From Passive to Persuasive: Localized Activation Injection for Empathy and Negotiationcited by 2
  11. 2025Evaluating Human-LLM Representation Alignment: A Case Study on Affective Sentence Generation for Augmentative and Alternative Communicationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Emotion2Skill: Model-Internal Emotion Signals for Adaptive Skill Selection and Evolutioncited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025Emotional Cognitive Modeling Framework with Desire-Driven Objective Optimization for LLM-empowered Agent in Social Simulation
  2. 2025Emergence of Hierarchical Emotion Organization in Large Language Models
  3. 2025Large language models show fragile cognitive reasoning about human emotions
  4. 2026How Affect Propagates among LLM Agents: Emergent Emotional Contagion in Crowd Simulation
  5. 2025Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models
  6. 2025From Rational Answers to Emotional Resonance: The Role of Controllable Emotion Generation in Language Models
  7. 2026On Emotion-Sensitive Decision Making of Small Language Model Agents
  8. 2026Emotion Concepts and their Function in a Large Language Model