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 note on the door was the first sign. “Your vehicle illegally parked. Towed.” Emily’s breath hitched. Her ancient, but beloved, Volvo was gone. Her neighbor, a man who consistently complained about everything, was behind this. The street was technically public, but parking was never an issue.

Her hands clenched. She had a list. A list of petty grievances. She started with his morning newspaper, strategically placed so it would be drenched by the sprinklers. The list grew longer with each passing hour. A cleverly timed complaint to the HOA about his overgrown hedges. A gentle suggestion about the legality of his oversized dog. The war, she decided, was on.

Emotion: vengeful

Cluster: Defiance / Spite
PC1 (Valence): 1.70 Positive
PC2 (Disposition): 3.71

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.739
la0.527
l0.507
😈0.422
-0.379
Suppressed:
own-0.981
此刻-0.504
గుర్త-0.464
보니-0.454
仿佛-0.442