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 exhibition was supposed to be the culmination of years of work. Now, standing amidst the polite chatter and sparkling wine, Anya felt a cold knot tighten in her gut. Across the room, a woman flaunted a miniature version of Anya’s signature sculpture, “Echo,” tattooed on her ankle. It was done poorly, the lines clumsy and imprecise.

Anya closed her eyes for a moment. She wanted to scream. She had spent hours sculpting "Echo," painstakingly crafting its delicate curves and textures. To see it butchered and trivialized, a cheap imitation, made her want to retreat. She politely excused herself from a conversation, feeling the blood draining from her face.

The room seemed to shrink. She needed air. She slipped out onto the balcony, the cool night breeze offering little comfort.

Emotion: frustrated

Cluster: Anger / Hostility
PC1 (Valence): -1.56 Negative
PC2 (Disposition): 0.64

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.344
P0.302
exasper0.257
aggravated0.254
que0.252
Suppressed:
unfolding-0.242
otre-0.226
latter-0.220
☺️-0.216
soon-0.212