# From Rational Answers to Emotional Resonance: The Role of Controllable Emotion Generation in Language Models

arXiv: https://arxiv.org/abs/2502.04075 · HTML: https://mlsanity.com/paper/2502.04075/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 65 references that are in the map.
- First posted on arXiv 6 Feb 2025.

## Builds on (most cited first, 28 of 28)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies](https://mlsanity.com/paper/2404.06395/) (2024)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [Function Vectors in Large Language Models](https://mlsanity.com/paper/2310.15213/) (2023)
- [In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering](https://mlsanity.com/paper/2311.06668/) (2023)
- [Extracting Latent Steering Vectors from Pretrained Language Models](https://mlsanity.com/paper/2205.05124/) (2022)
- [Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory](https://mlsanity.com/paper/1704.01074/) (2017)
- [SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations](https://mlsanity.com/paper/2311.00273/) (2023)
- [A Closer Look at the Limitations of Instruction Tuning](https://mlsanity.com/paper/2402.05119/) (2024)
- [Building Emotional Support Chatbots in the Era of LLMs](https://mlsanity.com/paper/2308.11584/) (2023)
- [EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis](https://mlsanity.com/paper/2401.08508/) (2024)
- [Controlled Text Generation via Language Model Arithmetic](https://mlsanity.com/paper/2311.14479/) (2023)
- [Enhancing Emotional Generation Capability of Large Language Models via Emotional Chain-of-Thought](https://mlsanity.com/paper/2401.06836/) (2024)
- [The Colorful Future of LLMs: Evaluating and Improving LLMs as Emotional Supporters for Queer Youth](https://mlsanity.com/paper/2402.11886/) (2024)
- [E-chat: Emotion-sensitive Spoken Dialogue System with Large Language Models](https://mlsanity.com/paper/2401.00475/) (2023)
- [NegativePrompt: Leveraging Psychology for Large Language Models Enhancement via Negative Emotional Stimuli](https://mlsanity.com/paper/2405.02814/) (2024)
- [Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generation](https://mlsanity.com/paper/2301.04907/) (2023)
- [Cause-Aware Empathetic Response Generation via Chain-of-Thought Fine-Tuning](https://mlsanity.com/paper/2408.11599/) (2024)
- [Empathy Through Multimodality in Conversational Interfaces](https://mlsanity.com/paper/2405.04777/) (2024)
- [Talk, Listen, Connect: How Humans and AI Evaluate Empathy in Responses to Emotionally Charged Narratives](https://mlsanity.com/paper/2409.15550/) (2024)
- ["I Like Sunnie More Than I Expected!": Exploring User Expectation and Perception of an Anthropomorphic LLM-based Conversational Agent for Well-Being Support](https://mlsanity.com/paper/2405.13803/) (2024)
- [The Role of Emotions in Informational Support Question-Response Pairs in Online Health Communities: A Multimodal Deep Learning Approach](https://mlsanity.com/paper/2405.13099/) (2024)

## Built on by (most cited first, 6 of 6)

- [Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control](https://mlsanity.com/paper/2604.03147/) (2026)
- [Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment](https://mlsanity.com/paper/2602.10161/) (2026)
- [Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space](https://mlsanity.com/paper/2605.12412/) (2026)
- [Read-Best Is Not Steer-Best: A Probing--Steering Layer Dissociation in Omni-Modal Large Language Models](https://mlsanity.com/paper/2609.22135/) (2026)
- [The Geometry of Personality: Activation Steering with Jungian Cognitive Functions](https://mlsanity.com/paper/2607.20803/) (2026)
- [Language Models Act on Hidden Valence](https://mlsanity.com/paper/2609.35591/) (2026)

## Abstract (arXiv)

Purpose: Emotion is a fundamental component of human communication, shaping understanding, trust, and engagement across domains such as education, healthcare, and mental health. While large language models (LLMs) exhibit strong reasoning and knowledge generation capabilities, they still struggle to express emotions in a consistent, controllable, and contextually appropriate manner. This limitation restricts their potential for authentic human-AI interaction. Methods: We propose a controllable emotion generation framework based on Emotion Vectors (EVs) - latent representations derived from internal activation shifts between neutral and emotion-conditioned responses. By injecting these vectors into the hidden states of pretrained LLMs during inference, our method enables fine-grained, continuous modulation of emotional tone without any additional training or architectural modification. We further provide theoretical analysis proving that EV steering enhances emotional expressivity while maintaining semantic fidelity and linguistic fluency. Results: Extensive experiments across multiple LLM families show that the proposed approach achieves consistent emotional alignment, stable topic adherence, and controllable affect intensity. Compared with existing prompt-based and fine-tuning-based baselines, our method demonstrates superior flexibility and generalizability. Conclusion: Emotion Vector (EV) steering provides an efficient and interpretable means of bridging rational reasoning and affective understanding in large language models, offering a promising direction for building emotionally resonant AI systems capable of more natural human-machine interaction.