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).

She found the list tucked inside his wallet. "Learn to play the guitar." Her vision tunneled. "Visit Iceland." She felt a sudden, sharp pain in her head. The simple list, a collection of hopes and dreams, felt like an act of war.

She stared at the list, her eyes darting from word to word. Each entry was a fresh wound. She felt a rising tide of panic, a desperate need to flee, to escape the suffocating room. She couldn't breathe.

She stumbled to the door, pulling it open and rushing into the street. The world was a cacophony of sound and movement. Her head pounded, and her legs felt like lead. She felt as though she might shatter.

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