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).

Sweat prickled on Amelia’s brow as she waited. The air in the coffee shop, usually a comfort, felt thick and suffocating. Her fingers drummed a frantic rhythm against the smooth, cold surface of the table. She kept checking her watch, each tick of the second hand a tiny hammer blow against her patience. The cafe's cheerful chatter sounded like a distant, distorted blur. A text notification pinged, and she snatched her phone. "Party's off. Something came up. So sorry." Her breath hitched, a strangled sound. She crumpled the text message in her fist, her knuckles white.

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