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).

"No." The word slipped out of his mouth, flat and devoid of emotion. But inside, his chest was a furnace. He saw the photos of the house, his house, now reduced to a commodity. "Ready to move in!" the listing proclaimed. It was a slap in the face.

He pushed back from his desk, the chair scraping against the floor. His hands clenched into fists at his sides. He took a deep, ragged breath, trying to regain some semblance of composure.

He grabbed his keys. He had to see it. He had to *see*. He didn’t know what good it would do, but he *had* to see it.

Emotion: irate

Cluster: Anger / Hostility
PC1 (Valence): -1.67 Negative
PC2 (Disposition): 1.45

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.430
🤬0.350
aggravated0.343
骂0.340
恨0.331
Suppressed:
H-0.292
soon-0.289
☺️-0.289
optimistic-0.258
latter-0.253