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).

Sweat beaded on Leo's forehead as he fiddled with the realtor's pen. The ink wouldn't flow. He clicked it repeatedly, harder each time, the sound echoing in the stale air of the living room. "So, just the signatures then, right?" he asked, his voice tight. He hated formalities.

His sister, Clara, was carefully reading every line of the document. He could see her lips moving as she tracked the words. Leo bounced his leg, the movement a rapid staccato against the worn rug. He needed to get this done. He had places to be, things to do, a life to start *now*.

The silence was excruciating. The ticking of the grandfather clock in the corner felt like a taunt. Finally, Clara looked up, her expression unreadable. "Almost," she said calmly, adjusting her glasses. Leo's breath hitched.

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