# Functional Emotions or Situational Contexts? A Discriminating Test from the Mythos Preview System Card

arXiv: https://arxiv.org/abs/2604.13466 · HTML: https://mlsanity.com/paper/2604.13466/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- Builds on 5 of its 7 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Placed in

- Mechanistic interpretability / [Activation steering methods](https://mlsanity.com/mechinterp/activation-steering-methods/)

## Builds on (most cited first, 5 of 5)

- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Auditing language models for hidden objectives](https://mlsanity.com/paper/2503.10965/) (2025)
- [AI Arms and Influence: Frontier Models Exhibit Sophisticated Reasoning in Simulated Nuclear Crises](https://mlsanity.com/paper/2602.14740/) (2026)

## Built on by (most cited first, 3 of 3)

- [Replicating the Geometry of Emotion Representations in a Base Open-Weights Model](https://mlsanity.com/paper/2609.22208/) (2026)
- [Same Outcome, Different Readout: What Does a Steerable Valence Direction in LLMs Represent?](https://mlsanity.com/paper/2609.22850/) (2026)
- [From cacophony to hierarchy: a principled framework for assessing AI consciousness](https://mlsanity.com/paper/2609.35618/) (2026)

## Abstract (arXiv)

The Claude Mythos Preview system card deploys emotion vectors, sparse autoencoder (SAE) features, and activation verbalisers to study model internals during misaligned behaviour. The two primary toolkits are not jointly reported on the most alignment-relevant episodes. This note identifies two hypotheses that are qualitatively consistent with the published results: that the emotion vectors track functional emotions that causally drive behaviour, or that they are a projection of a richer situational-context structure onto human emotional axes. The hypotheses can be distinguished by cross-referencing the two toolkits on episodes where only one is currently reported: most directly, applying emotion probes to the strategic concealment episodes analysed only with SAE features. If emotion probes show flat activation while SAE features are strongly active, the alignment-relevant structure lies outside the emotion subspace. Which hypothesis is correct determines whether emotion-based monitoring will robustly detect dangerous model behaviour or systematically miss it.