# AI shares emotion with humans across languages and cultures

arXiv: https://arxiv.org/abs/2506.13978 · HTML: https://mlsanity.com/paper/2506.13978/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 80 references that are in the map.
- First posted on arXiv 11 Jun 2025.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Scaling and evaluating sparse autoencoders](https://mlsanity.com/paper/2406.04093/) (2024)
- [Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2](https://mlsanity.com/paper/2408.05147/) (2024)
- [Role-Play with Large Language Models](https://mlsanity.com/paper/2305.16367/) (2023)
- [AI Alignment: A Comprehensive Survey](https://mlsanity.com/paper/2310.19852/) (2023)
- [AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders](https://mlsanity.com/paper/2501.17148/) (2025)
- [Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders](https://mlsanity.com/paper/2410.20526/) (2024)
- [Learnable latent embeddings for joint behavioral and neural analysis](https://mlsanity.com/paper/2204.00673/) (2022)
- [Building Machines that Learn and Think with People](https://mlsanity.com/paper/2408.03943/) (2024)
- [Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering](https://mlsanity.com/paper/2410.15999/) (2024)
- [A Systematic Review on Affective Computing: Emotion Models, Databases, and Recent Advances](https://mlsanity.com/paper/2203.06935/) (2022)
- [Steering Large Language Model Activations in Sparse Spaces](https://mlsanity.com/paper/2503.00177/) (2025)
- [Machine Culture](https://mlsanity.com/paper/2311.11388/) (2023)
- [Large Language Models in Mental Health Care: a Scoping Review](https://mlsanity.com/paper/2401.02984/) (2024)
- [A new sociology of humans and machines](https://mlsanity.com/paper/2402.14410/) (2024)
- [Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective](https://mlsanity.com/paper/2408.04638/) (2024)
- [Exploring the Personality Traits of LLMs through Latent Features Steering](https://mlsanity.com/paper/2410.10863/) (2024)
- [Language-Specific Representation of Emotion-Concept Knowledge Causally Supports Emotion Inference](https://mlsanity.com/paper/2302.09582/) (2023)

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

- [Emotion Concepts and their Function in a Large Language Model](https://mlsanity.com/paper/2604.07729/) (2026)
- [Inducing State Anxiety in LLM Agents Reproduces Human-Like Biases in Consumer Decision-Making](https://mlsanity.com/paper/2510.06222/) (2025)
- [On Emotion-Sensitive Decision Making of Small Language Model Agents](https://mlsanity.com/paper/2604.06562/) (2026)
- [The Grounding Gap: How LLMs Anchor the Meaning of Abstract Concepts Differently from Humans](https://mlsanity.com/paper/2605.08837/) (2026)
- [A Navigable Manifold of Hypothesized Consciousness-Spectrum States in Language Model Representations](https://mlsanity.com/paper/2606.09894/) (2026)
- [Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?](https://mlsanity.com/paper/2607.12631/) (2026)

## Abstract (arXiv)

Effective and safe human-machine collaboration requires the regulated and meaningful exchange of emotions between humans and artificial intelligence (AI). Current AI systems based on large language models (LLMs) can provide feedback that makes people feel heard. Yet it remains unclear whether LLMs represent emotion in language as humans do, or whether and how the emotional tone of their output can be controlled. We assess human-AI emotional alignment across linguistic-cultural groups and model-families, using interpretable LLM features translated from concept-sets for over twenty nuanced emotion categories (including six basic emotions). Our analyses reveal that LLM-derived emotion spaces are structurally congruent with human perception, underpinned by the fundamental affective dimensions of valence and arousal. Furthermore, these emotion-related features also accurately predict large-scale behavioural data on word ratings along these two core dimensions, reflecting both universal and language-specific patterns. Finally, by leveraging steering vectors derived solely from human-centric emotion concepts, we show that model expressions can be stably and naturally modulated across distinct emotion categories, which provides causal evidence that human emotion concepts can be used to systematically induce LLMs to produce corresponding affective states when conveying content. These findings suggest AI not only shares emotional representations with humans but its affective outputs can be precisely guided using psychologically grounded emotion concepts.