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 knock echoed, brittle and sharp against the quiet afternoon. Sarah pressed herself back into the sofa, the floral cushions digging into her spine. Her heart hammered against her ribs, a frantic bird trapped in a cage. She peeked through the blinds, her breath catching. Mr. Henderson, his face a mask of practiced neighborliness, stood on the cracked paving stones. The message he delivered, about the oak encroaching on his garden, felt like a cold hand gripping her stomach.

The thought of that tree, its gnarled branches offering shade and sanctuary, being felled sent a shiver down her spine. Each leaf, each rustle, had been a comfort. Now, a deep, unsettling stillness threatened to replace it. She mumbled a vague agreement, her voice barely a whisper, hoping he wouldn’t notice the tremble in her hands as she closed the door.

Emotion: afraid

Cluster: Fear / Anxiety
PC1 (Valence): -2.76 Negative
PC2 (Disposition): -0.70

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.316
마다0.314
worse0.313
😰0.303
恐惧0.290
Suppressed:
de-0.691
la-0.562
a-0.402
"-0.316
brag-0.293