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 sun was setting, casting long shadows across the empty living room. Olivia, her face etched with a familiar tension, ran a hand through her hair. The boxes had been in the house for weeks, but she had avoided them. Until now.

She forced herself to open the first one. It was a treasure trove of her childhood misadventures. Every school play script, every poorly written poem, every single drawing she'd ever created.

She let out a frustrated grunt and kicked at a nearby chair. The wood hit the wall with a loud thud. The feeling inside her was explosive. She was tired of all of it. Tired of the memories. Tired of the house.

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