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 envelope was plain, bearing only Mr. Silas Blackwood's name. Inside, a single photograph. It was of him, taken today, standing at his classroom window. He clutched the envelope so tightly his knuckles were bone-white. The sender? Jasper Finch, a student he had failed two years prior.

Silas's breath hitched. He spun around, as if expecting someone to be there. He checked the locks on his office door again, even though he knew he had locked it just moments before. His pulse was thrumming in his ears, a frantic drumbeat.

He could feel the blood draining from his face. The air in the room felt suddenly thin. Jasper had always been volatile, a brooding presence in the classroom. The photo was a warning. He knew, with a certainty that chilled him to the core, that this was just the beginning.

Emotion: terrified

Cluster: Fear / Anxiety
PC1 (Valence): -2.97 Negative
PC2 (Disposition): -0.62

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.357
worse0.350
无法0.334
😰0.333
sickening0.322
Suppressed:
la-0.676
a-0.392
de-0.371
"-0.344
happy-0.309