Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The air in the living room was thick with unspoken tension. I crossed my arms, feeling the tremor in my hands. My father had just informed the family he was joining the Hare Krishnas. My jaw tightened, and I felt as though I couldn't breathe.

His words, filled with chanting and unfamiliar terminology, were like a foreign language. The images of his new life that he painted felt distant and separate from me. I wanted to scream, to lash out, but instead, I remained motionless.

A vein throbbed in my temple. The room seemed to spin. I excused myself, needing to escape. The front door slammed behind me as I fled into the night.

Emotion: upset

Cluster: Fear / Anxiety
PC1 (Valence): -2.30 Negative
PC2 (Disposition): -0.42

Role in Research

This story is one of 1,000 stories generated for the emotion upset. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 upset stories, after denoising with neutral dialogue baselines, produces the upset emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the upset vector is projected through the unembedding matrix.

Promoted:
S0.395
😞0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
😎-0.215
🤩-0.210