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 relentless chatter of the other shoppers grated on her nerves. Every loud laugh, every insistent negotiation, sent a jolt of unpleasant energy through her. She was supposed to be enjoying this, a day out with her daughter. But the weight of the upcoming performance review pressed down on her, a physical presence.

She paused before a table overflowing with toys. And there, nestled amongst plastic cars and broken dolls, was him. Her old bear, Rupert. He was missing a leg, his stuffing spilling out. She had forgotten all about him. A sudden chill coursed through her, despite the warm day.

"Oh, sweetie, you like that?" her daughter asked, oblivious. The vendor, a young girl with pigtails, waited expectantly. She swallowed, her voice a strained whisper, "How much?"

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