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 trembled in Amelia's hand, sloshing dark liquid onto the table. She stared at the overflowing cup, then at the clock, then at the empty space where Professor Davies should have been. Her foot tapped a staccato rhythm against the linoleum floor. The meeting had been moved at the last second, and she felt her temper flaring. She wanted her advisor to sign off on her draft. She had waited for months.

A curt knock interrupted her internal monologue.

"Amelia?" Professor Davies’ voice, clipped and formal.

"Yes, Professor." Amelia’s reply was clipped and sharp.

He entered, his gaze avoiding hers. "I've been offered a position in the private sector. I will be leaving at the end of the semester."

Amelia's chest tightened. All those hours of work. All that waiting...

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