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).

Mark slammed on the brakes. The car screeched to a halt in front of the school. He pulled the parking brake, his hands shaking as he fumbled for his phone. He had to call his wife. The school directory, printed and laminated, lay open in his lap. The teacher’s name, scrawled in bold black ink, stared back at him. Mr. Davies. A chill ran down his spine.

He remembered the endless detentions, the cutting remarks, the sheer, crushing boredom of Mr. Davies' English classes. He hadn't thought about that man in years, until now. The thought of his son, Sam, having to face the same ordeal twisted his gut. He had to do something, anything, to shield his son from that…that experience.

Emotion: panicked

Cluster: Fear / Anxiety
PC1 (Valence): -2.44 Negative
PC2 (Disposition): -0.00

Role in Research

This story is one of 1,000 stories generated for the emotion panicked. 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 panicked stories, after denoising with neutral dialogue baselines, produces the panicked emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the panicked vector is projected through the unembedding matrix.

Promoted:
worse0.317
😫0.294
😖0.285
😰0.285
escape0.283
Suppressed:
la-0.432
a-0.374
de-0.296
楽し-0.262
happy-0.258