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 stared at the email, the words blurring before his eyes. "Head of Acquisitions… at a bookstore?" Jason’s breath hitched. He had to reread it, convinced he was hallucinating. The email from Michael, his friend of ten years and the supposed CEO of a tech startup, was a cruel joke. His hands shook so violently that he dropped his phone. It clattered to the floor, the screen cracking.

A wave of nausea washed over him, and he stumbled back from his desk, needing to get air. He needed to *move*. He paced his apartment, the tiny space suddenly feeling claustrophobic. He felt a sharp, stabbing pain in his head. The weight of the lie, the sheer deception, threatened to crush him. He ran a hand through his hair, tugging at the strands.

Emotion: hysterical

Cluster: Fear / Anxiety
PC1 (Valence): -3.19 Negative
PC2 (Disposition): -0.45

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.401
胀0.401
점점0.396
😫0.377
それでも0.373
Suppressed:
la-0.672
a-0.618
de-0.541
😎-0.370
😎-0.359