# Controllable Affective Generation via Latent Vector Steering

arXiv: https://arxiv.org/abs/2608.25569 · HTML: https://mlsanity.com/paper/2608.25569/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 59 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Builds on (most cited first, 30 of 30)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [Understanding the Effects of RLHF on LLM Generalisation and Diversity](https://mlsanity.com/paper/2310.06452/) (2023)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Social Chemistry 101: Learning to Reason about Social and Moral Norms](https://mlsanity.com/paper/2011.00620/) (2020)
- [Large Language Models Understand and Can be Enhanced by Emotional Stimuli](https://mlsanity.com/paper/2307.11760/) (2023)
- [CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling](https://mlsanity.com/paper/2405.16433/) (2024)
- [NormBank: A Knowledge Bank of Situational Social Norms](https://mlsanity.com/paper/2305.17008/) (2023)
- [Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens](https://mlsanity.com/paper/2505.18237/) (2025)
- [Evaluating the Prompt Steerability of Large Language Models](https://mlsanity.com/paper/2411.12405/) (2024)
- [Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective](https://mlsanity.com/paper/2408.04638/) (2024)
- [Fine-grained Affective Processing Capabilities Emerging from Large Language Models](https://mlsanity.com/paper/2309.01664/) (2023)
- [R2MED: A Benchmark for Reasoning-Driven Medical Retrieval](https://mlsanity.com/paper/2505.14558/) (2025)
- [Training language models to be warm and empathetic makes them less reliable and more sycophantic](https://mlsanity.com/paper/2507.21919/) (2025)
- [MoHoBench: Assessing Honesty of Multimodal Large Language Models via Unanswerable Visual Questions](https://mlsanity.com/paper/2507.21503/) (2025)
- [Reinforcement Learning from Human Feedback: Whose Culture, Whose Values, Whose Perspectives?](https://mlsanity.com/paper/2407.17482/) (2024)
- [AutoMIR: Effective Zero-Shot Medical Information Retrieval without Relevance Labels](https://mlsanity.com/paper/2410.20050/) (2024)
- [Tricolore: Multi-Behavior User Profiling for Enhanced Candidate Generation in Recommender Systems](https://mlsanity.com/paper/2505.02120/) (2025)
- [SoREX: Towards Self-Explainable Social Recommendation with Relevant Ego-Path Extraction](https://mlsanity.com/paper/2510.00080/) (2025)
- [Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation](https://mlsanity.com/paper/2510.09275/) (2025)
- [The Effectiveness of Style Vectors for Steering Large Language Models: A Human Evaluation](https://mlsanity.com/paper/2601.21505/) (2026)
- [Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities](https://mlsanity.com/paper/2604.05339/) (2026)
- [Why not Collaborative Filtering in Dual View? Bridging Sparse and Dense Models](https://mlsanity.com/paper/2601.09286/) (2026)
- [Intelli-Planner: Towards Customized Urban Planning via Large Language Model Empowered Reinforcement Learning](https://mlsanity.com/paper/2601.21212/) (2026)
- [HypeMed: Enhancing Medication Recommendations with Hypergraph-Based Patient Relationships](https://mlsanity.com/paper/2603.18459/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) often produce emotionally flattened responses after alignment, limiting their effectiveness in affect-sensitive applications. In this paper, we propose EmoVec, a lightweight framework for controllable affective generation via latent vector steering. EmoVec extracts emotion-specific directions from paired neutral and emotion-conditioned responses using contrastive activation addition, and further refines them through task-specific debiasing and principal subspace removal. During inference, these vectors are injected into the final residual stream with static or scenario-adaptive scaling, enabling continuous control over emotional intensity without updating model weights. Experiments across three LLMs and eight emotions show that EmoVec consistently improves emotional salience while largely preserving semantic content, fluency, and coherence. Ablation studies and human evaluation further confirm the effectiveness of vector purification and adaptive scaling, establishing EmoVec as a practical inference-time method for affective control in deployed LLMs.