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 always been the golden boy. Mark, the supposed corporate lawyer. Now, standing outside the dive bar where they’d planned to celebrate Mark’s "big promotion," Daniel felt a chill despite the humid summer night. He’d just seen Mark – no, not Mark, *Marcus* as the fancy nametag read – working the drive-thru window at a Taco Bell. The knot in Daniel’s stomach tightened. He’d spent years listening to Marcus’s boasts about high-powered court cases and six-figure salaries. He balled his fists, the cheap fabric of his shirt bunching beneath them.

Emotion: bitter

Cluster: Shame / Guilt
PC1 (Valence): -1.78 Negative
PC2 (Disposition): 0.84

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.447
striving0.238
😞0.236
aggravated0.225
soport0.223
Suppressed:
own-0.316
de-0.291
la-0.231
🤩-0.227
是非常-0.225