# What We Talk About When We Talk About Emotion Editing

arXiv: https://arxiv.org/abs/2610.13558 · HTML: https://mlsanity.com/paper/2610.13558/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 29 references that are in the map.
- First posted on arXiv 9 Oct 2026.

## Builds on (most cited first, 15 of 15)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [ReFT: Representation Finetuning for Language Models](https://mlsanity.com/paper/2404.03592/) (2024)
- [Learning From Brains How to Regularize Machines](https://mlsanity.com/paper/1911.05072/) (2019)
- [Language-Driven Image Style Transfer](https://mlsanity.com/paper/2106.00178/) (2021)
- [EmoEdit: Evoking Emotions through Image Manipulation](https://mlsanity.com/paper/2405.12661/) (2024)
- [Make Me Happier: Evoking Emotions Through Image Diffusion Models](https://mlsanity.com/paper/2403.08255/) (2024)
- [A foundation model of vision, audition, and language for in-silico neuroscience](https://mlsanity.com/paper/2605.04326/) (2026)
- [Beyond representational alignment with brain-guided language models for robust reasoning](https://mlsanity.com/paper/2606.11893/) (2026)
- [Calibrated Harmonic Overlaid Implicit Neural Representations for Multi-Dimensional Data](https://mlsanity.com/paper/2606.26763/) (2026)
- [What Can I Edit? Open-Ended Strategy Discovery and the Emotion Editability Landscape](https://mlsanity.com/paper/2607.23920/) (2026)
- [AffectDelta: Beyond Emotion Labels for Image Editing](https://mlsanity.com/paper/2609.02616/) (2026)

## Abstract (arXiv)

Emotional image editing aims to change the emotion a scene conveys while preserving its essential content. Because the same scene can support different emotional interpretations, achieving an emotional goal requires visual changes grounded in the source context. Motivated by the Component Process Model, which links emotional responses to event appraisal, we investigate neural representations as a reference for these editing decisions. Using TRIBE v2, an fMRI encoding model, we analyze 400 source-target pairs across eight emotion categories. Hidden states from EmoEdit, EmoEditor, and AffectDelta correspond more strongly to predicted target-image responses in visual regions than in affect-related regions. This imbalance motivates ROI-ReFT, which combines source visual responses as a content reference with a predicted affective response change as an editing direction. Two interacting branches use both conditions to guide a frozen editor throughout generation. Predicted responses of the generated image supervise affective change and constrain visual drift. On a post hoc selected subset of 400 editing requests, ROI-ReFT achieves 91.75% target-emotion accuracy and 83.25% joint success, with the same output both matching the target emotion and reaching source-output DINO-I of at least 0.80. Our code and dataset will be publicly released.