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 email from Marcus arrived just as Amelia was starting her coffee. It contained a slideshow of old photos from their university days. One picture in particular, of them both at a frat party, brought a wave of nausea to Amelia’s stomach. She read the caption: "Remember that time we got so wasted and you ended up dancing on the table?"

Amelia reeled. She remembered the party, sure. The loud music, the crowded room, the free-flowing drinks. But she recalled a night of quiet conversation and early departure. She remembered the way she'd politely declined the insistent demands for her to drink more. She had a distinct memory of leaving early to go study in the library. Amelia’s hand trembled as she grabbed her phone, her fingers fumbling over the keyboard.

Emotion: shocked

Cluster: Surprise / Confusion
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
будто0.298
😰0.268
sickening0.266
не0.266
que0.257
Suppressed:
enthusi-0.283
开心-0.269
ولة-0.262
ارك-0.257
উৎসাহিত-0.255