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 thickened in the small study. Ava had found the manuscript in a locked drawer. "The Prism of Ethan" was the title, a phrase that felt like a punch to the gut. The story was familiar, too familiar, chronicling the slow crumbling of their relationship.

She felt a wave of nausea wash over her. Her hands trembled as she read about their arguments, their silences, the widening chasm between them. The fictional Ethan was distant, cold, and cruel.

A bitter taste filled her mouth. She had to know how it ended, even as each word chipped away at her. A cold sweat slicked her skin. The urge to smash something, anything, consumed her.

Emotion: scared

Cluster: Fear / Anxiety
PC1 (Valence): -2.86 Negative
PC2 (Disposition): -0.84

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.350
😰0.337
😖0.317
마다0.317
恐惧0.311
Suppressed:
la-0.637
de-0.605
a-0.402
"-0.351
happy-0.314