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 humid air of the solicitor's office seemed to press down on Leo. He kept tugging at his tie, the silk a foreign object against his skin. This whole charade was absurd. Their father, a man of such meticulous planning, should have left something, anything, straightforward. Yet here they were, sifted through a mountain of paperwork, the lawyer droning on.

"…and then there's this, a collection of vintage toy soldiers, appraised at a nominal value…"

Leo scoffed under his breath. Nominal? His sister, Clara, across the mahogany table, gave him a pointed look. He crossed his arms, the slight tension in his shoulders telling the whole story. He wanted to be anywhere but there.

"…and finally, a rather unusual bequest for you, Mr. Leo. A small plot of land… on the moon."

Emotion: irritated

Cluster: Anger / Hostility
PC1 (Valence): -0.86 Negative
PC2 (Disposition): 1.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.370
S0.282
P0.264
😠0.248
aggravated0.233
Suppressed:
own-0.300
joyful-0.211
joyous-0.207
खोले-0.206
newfound-0.205