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 bland, official announcement was still clutched in her hand, a crumpled paper testament to the violation she felt. The words "market value" and "investment opportunity" echoed in her head, twisting her insides. She felt a cold dread settling in her bones.

She marched into the kitchen and yanked open the refrigerator. She didn't want anything. She just needed to *do* something. She slammed the door shut again, the force of the action reverberating through the small room.

She let out a frustrated grunt and dropped into a chair, her shoulders slumped. The world suddenly felt heavy, overwhelming. The walls seemed to be closing in on her.

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