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 clatter of the watering can against the cobblestone path nearly made Elias jump. His hands, usually steady, were fumbling with the nozzle, struggling to get a good spray. Mrs. Gable, a woman who always seemed to carry a sunbeam in her smile, was at his gate.

"Elias, dear," she called, her voice bright. "Such lovely tomatoes you have! Say, I was wondering…"

His jaw clenched. He adjusted his glasses, then rubbed a hand across his forehead. A bead of sweat trickled down his temple. He knew where this was going.

“Yes, Mrs. Gable?” he asked, trying to sound pleasant, but his voice came out a little too tight. The sun, suddenly, felt oppressively warm on his back.

Emotion: tense

Cluster: Fear / Anxiety
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.213
😰0.191
느껴0.183
😣0.183
😖0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198