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).

"Just open it, Liam," his wife had pleaded, her voice a gentle coaxing. He'd simply grunted in response, fiddling with the car keys, his fingers picking at the metal. The thick envelope, addressed in a familiar, yet distant hand, sat on the kitchen counter like a forgotten burden. The breakfast dishes remained unwashed. He glanced at the clock on the microwave, a sudden, urgent desire to be *anywhere* else consuming him.

He ripped the envelope open, his actions lacking grace. The words, carefully chosen, did little to soothe the coiled tension in his chest. A muscle in his jaw ticked. He crumpled the paper, throwing it in the bin with deliberate force.

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