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 school cafeteria was filled with the boisterous chatter of children, a noise that grated on Ms. Bell. She had spent the entire morning dealing with disruptive behaviors. She felt a surge of bitterness towards the school system, the students, and the world itself. On her desk, a small, silver box. It was a gift.

She picked it up with a sense of dread, and threw it towards the nearest trash can. The box didn't make it. It hit the wall, and the contents, a small, silver charm bracelet, spilled out. A note, tucked inside, read, “Thanks for being a star, Ms. Bell.” Her face contorted.

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