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 beaded on Liam's forehead as he slammed the pawn shop door shut. The bell above it gave a mournful tinkle. He’d been hunting for hours, scouring dusty shelves and glass cases, each trinket a tiny stab of disappointment. He gripped the cheap, plastic steering wheel of his beat-up car, the vinyl hot against his palm. He needed to find something, anything, to make this day better. He'd blown the budget, a foolish mistake fueled by the pressure he felt. A sudden, sharp pain lanced through his shoulder – the old injury acting up again. This was a disaster.

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