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 engine coughed, sputtered, and died. He pounded the steering wheel, each blow echoing in the sudden quiet of the deserted road. It was already late, and he was miles from anywhere. He let out a groan.

He needed professional assistance. He'd been battling the demons of his past for years, feeling as though he was on the verge of collapsing. A close friend, a well-meaning acquaintance, recommended a therapist, a guy named Mark Henderson.

The name evoked a wave of bitter memories, the stinging memories of bullying and humiliation. He closed his eyes, the image of Henderson's sneering face vivid in his mind. The thought of vulnerability sent a chill up his spine.

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