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).

Liam stared at the email, the words blurring on the screen. Dr. Chen. Gone. He felt a cold knot tighten in his stomach. All that time, all the effort he'd put into Chen's pet project, the one that *Liam* had thought was a dead end. Now, Chen was off to greener pastures and Liam was left holding the bag of stale data.

The library’s fluorescent lights seemed to hum with malice. He grabbed the professor's old files, the ones that had been stashed away, hidden from view.

Liam knew Dr. Chen was expecting him to defend a paper at the conference. Well, it would be a shame if that defense didn't go as planned.

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