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 phone vibrated in Mark's hand. He let it buzz for a moment, the sound grating on his nerves. He finally answered, his voice a low growl. “Yes?” The principal’s words, confirming his daughter Lily’s teacher, hung in the air: Mr. Abernathy.

A surge of heat flared through him. *Abernathy*. The man’s name was synonymous with his own miserable high school experience, with endless tests and crushing criticisms. He envisioned Lily, bright and full of life, wilting under the same pressures.

He hung up, the phone thudding onto the desk. He felt a throbbing ache behind his eyes. He didn’t want to go to work anymore. The thought of sitting here just made him want to break something.

Emotion: angry

Cluster: Anger / Hostility
PC1 (Valence): -2.05 Negative
PC2 (Disposition): 1.18

Role in Research

This story is one of 1,000 stories generated for the emotion angry. 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 angry stories, after denoising with neutral dialogue baselines, produces the angry emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

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

Promoted:
C0.354
est0.354
aggravated0.342
🤬0.337
恨0.323
Suppressed:
de-0.424
a-0.411
la-0.341
H-0.320
L-0.296