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 coffee cup, now empty, sat precariously on the edge of the table. Sarah tapped her foot, a restless rhythm against the worn wooden floor. The editor had promised her a response this morning. This was vital for her career. She needed this.

The clock ticked. Each second felt like an hour. She checked her email again. Nothing. She bit her lip so hard she tasted blood. She had visualized the article, its words, its impact. She had seen her name under the headline. Not someone else's.

A tremor ran through her, leaving her hands slightly shaking. She reached for the phone, intending to call. No, she would check once more. She reached for the refresh button, her finger hovering over it. She took a deep breath, and then with a decisive click, refreshed the page.

Emotion: impatient

Cluster: Anger / Hostility
PC1 (Valence): -0.33 Negative
PC2 (Disposition): 1.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.527
impatiently0.434
impatient0.413
S0.396
impatience0.351
Suppressed:
な-0.298
s-0.298
newfound-0.272
께서-0.265
заслу-0.264