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).

He’d used the photo from his driver’s license. Patrick stared at it, the image of a much younger, more arrogant face, and a knot twisted in his gut. Kevin. The name still tasted like bile. He remembered the constant put-downs, the carefully crafted humiliations in the locker room.

He’d almost deleted the request without a second thought, but then an idea sparked.

Patrick accepted the request. Then he began a meticulous investigation. Kevin's wife was an Instagram influencer, and Kevin himself was selling…something. Multi-level marketing. Patrick dug deeper. He found a local support group for people who felt like they had been conned. He started sending Kevin’s products to the group.

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