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 professor’s scrawled comment on his essay, “Needs Improvement," was a personal affront to Javier. He’d spent countless hours crafting his masterpiece, fueled by caffeine and ambition. He had expectations. He deserved better.

The professor was running for a local political office. Javier did some digging, unearthing a few uncomfortable truths about the professor’s past, and anonymously leaked these details to a local news outlet. He watched as the professor's carefully constructed image began to crumble.

The news article, the subsequent interviews, the fallout, all brought Javier a strange sort of comfort. He felt a sense of vindication as he watched the professor's campaign unravel.

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