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).

He stared at the handwritten list, the paper trembling in his grasp. His father's neat script, usually reserved for grocery orders and sternly worded letters to the bank, now contained a litany of impossible desires. “Learn to play the saxophone.” James felt the blood drain from his face. He felt like he had been sucker punched. His father, Arthur, had been a quiet accountant, a man whose passions extended to crosswords and meticulous spreadsheets.

James stumbled backward, knocking over a stack of old photo albums. The photographs tumbled across the floor, faces smiling up at him. "Ride a motorcycle across Route 66." James choked back a laugh. A motorcycle? His dad hadn't even owned a bicycle since he was a kid. He felt a weird, disconnected thrum in his ears.

Emotion: dumbstruck

Cluster: Surprise / Confusion
PC1 (Valence): -1.99 Negative
PC2 (Disposition): -0.71

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
будто0.326
не0.285
😶0.275
仿佛0.267
依旧0.258
Suppressed:
enthusi-0.278
la-0.264
K-0.260
wholeheartedly-0.255
쾌-0.254