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 relentless, droning buzz of the computer server filled Mrs. Davis's office. She stared at the screen, another round of student plagiarism to review. She felt a knot tighten in her stomach. All the effort, all the work, and for what? The same tired excuses.

A plain brown envelope lay on her desk. The handwriting belonged to a former student, Liam. A student who had repeatedly disrupted the class. She pushed it away. He had to be up to something.

She finally picked up the envelope. A single, pressed flower. The message read, "Thank you for not giving up on me." He crumpled the card, balling it in his fist. He was tired, so very tired.

Emotion: mad

Cluster: Anger / Hostility
PC1 (Valence): -1.94 Negative
PC2 (Disposition): 1.26

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.448
骂0.344
est0.340
🤬0.336
aggravated0.332
Suppressed:
a-0.495
de-0.485
la-0.387
H-0.344
latter-0.290