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 metallic tang of blood filled Marco’s mouth as he stared at the flyer. "Personal Trainer - Fitness Guru." It was a bold claim for a man who, yesterday, had been struggling to lift a box of groceries at the supermarket. James, his "fitness guru" friend, the one always offering unsolicited advice and showing off his "muscles," was a liar.

He ran a hand through his hair, tugging at the strands. The pounding in his temples was relentless. He’d signed up for a training package, of course. He’d even spent a small fortune on the "nutritional supplements" James had recommended. The world seemed to tilt on its axis.

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