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 found the announcement tacked to the bulletin board in the student union, the paper crinkling under his furious grip. This wasn’t just a closure; it was an act of personal betrayal, a slap in the face after his years pouring his soul into the school's theatre program. He had sacrificed everything, and for what?

A sudden inspiration sparked in his mind. The final performance, their grand finale before the summer break? He'd rewrite it, transform it. The script would be a scathing indictment, a theatrical bomb of truths the administration wouldn't soon forget. He would make them see the wreckage they created.

The opening night was a disaster for them, the audience shifting uncomfortably, the administrators blanching in their seats. The final bow was met with a stunned silence, and then, slowly, a thunderous applause. His fury tasted sweet, like well-deserved praise.

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