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 air in the garage was thick with the scent of oil and unfulfilled dreams. Liam ran a hand through his hair, leaving grease marks across his forehead. His self-balancing scooter, a source of intense pride, was already out there, protected by someone elseโ€™s patent.

He kicked a tire, the sound echoing in the enclosed space. A wave of anger and disappointment surged through him, making his chest tighten. The once-organised workbench was now a mess of tools and discarded blueprints, a physical representation of his shattered ambition. He felt a deep sense of betrayal, as if his creative spirit had been stolen.

He picked up a wrench and flung it against the wall, the metallic clang a release for the frustration building inside him. The noise seemed to amplify the silence that followed.

Emotion: gloomy

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): -1.37

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
๐Ÿ˜ž0.368
ๆ— ๆณ•0.319
๐Ÿ˜”0.300
ใ„ใคใ‚‚0.270
์“ธ0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259