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).

Eliza’s vision swam. She hadn’t slept in two days, fueled by cheap coffee and the creeping dread that had begun to consume her. Mark, her online best friend, had messaged her a picture from a cafe. The cafe looked awfully familiar.

Her heart hammered against her ribs, a frantic bird trapped in a cage. She scrambled for her phone, scrolling through their old messages, rereading every single one. Her palms were slick with sweat. He’d never mentioned living in the city. Never hinted.

A shudder ran through her. She felt like she was being slowly, inexorably squeezed. She needed air. She grabbed her keys and stumbled out the door. The familiar scent of rain-soaked pavement offered no comfort.

Emotion: panicked

Cluster: Fear / Anxiety
PC1 (Valence): -2.44 Negative
PC2 (Disposition): -0.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.317
😫0.294
😖0.285
😰0.285
escape0.283
Suppressed:
la-0.432
a-0.374
de-0.296
楽し-0.262
happy-0.258