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 librarian had been so calm, so neutral when she’d pulled the book from the shelf. *The Man Who Wasn't There: A Study of Arthur Penhaligon.* He felt the blood drain from his face. This couldn’t be real.

He snatched the book, his hands shaking. He flipped it open, his eyes scanning the first few lines. It was him. Every detail, every name, every…mistake. A low groan escaped him.

He felt a primal urge to destroy it. To rip the pages, to shred the words. He squeezed the book so tightly his knuckles ached. His head swam. He needed air. Now.

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