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).

He found himself pacing the worn rug in his father’s study, the ticking of the grandfather clock a maddening metronome keeping time with the furious thrum in his temples. His brother, Michael, had just told the family he was joining a synagogue. The audacity! After all this time, all this effort they had put into establishing their family traditions. Each footfall on the wooden floorboards resonated with the growing tension, a tangible thing that seemed to vibrate through his entire body. He slammed his fist on the desk, scattering a pile of neatly stacked papers. "You're betraying us all," he muttered under his breath, the accusation hanging heavy in the air.

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