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 news hit Ethan like a physical blow. He stood perfectly still for a moment, his body rigid, his eyes fixed on the screen. The air in the room seemed to thicken, making it difficult to breathe. He felt a sudden, sharp pain in his chest.

He slowly walked to the window, staring out at the vibrant world outside. He wanted to scream, to shatter the silence with his fury. The world’s happiness seemed to taunt him, its joy a cruel reminder of his disappointment.

He clenched his jaw, biting down hard to stop the tremor that was beginning in his legs. His entire body felt as though it was vibrating with suppressed energy.

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