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 air crackled with a strange energy. She couldn't sit still, her leg bouncing uncontrollably. Her fingers trembled as she typed out an email to HR, her thoughts a jumbled mess. How could they? How *dare* they? The injustice of it all burned in her chest.

She felt a wave of heat wash over her, her face flushing. She ripped the email up and threw it in the trash, her movements erratic and jerky. She needed to go, to breathe, to get away from this feeling of being trapped.

She ran out of her office, the flimsy door slamming shut behind her with a loud crack. She needed to do *something*. Anything.

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
่ƒ€0.401
์ ์ 0.396
๐Ÿ˜ซ0.377
ใใ‚Œใงใ‚‚0.373
Suppressed:
la-0.672
a-0.618
de-0.541
๐Ÿ˜Ž-0.370
๐Ÿ˜Ž-0.359