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 email notification on Amelia's phone vibrated incessantly. *Results are ready!* The subject line screamed. She gripped the worn leather of her couch, knuckles white. Three weeks. Three agonizing weeks since she'd spit into a tube, hoping for some flicker of connection to her past. Now, here it was. She jabbed at the screen, heart hammering against her ribs.

Her breath hitched as the website loaded. The spinning circle of doom. She tapped her foot, a frantic rhythm against the hardwood floor. Each revolution was a tiny, excruciating delay. "Come on, come on," she muttered under her breath.

Finally, the results appeared. A family tree, branching out with names she'd never heard before. She scanned the list of potential relatives, a buzzing sensation coursing through her. Who were these people? Were they anything like her? She was suddenly ravenous for answers.

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