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 scent of oil paints and turpentine filled the air. David stood before his easel, the canvas displaying a landscape nearly finished. His son, Noah, watched with an unwavering gaze, his own small sketchbook open. David wanted to get this painting done.

"Can I try blending the colors, Dad?" Noah asked, his voice a soft plea. David felt a rush of heat to his face.

"Not yet, Noah," he said, his voice curt. "This is very delicate, and it's taking me a long time." The pressure of the upcoming gallery showing felt heavy on his shoulders.

Noah's shoulders slumped. He closed his sketchbook, his enthusiasm deflating. The smell of paint, usually a comfort, felt thick and cloying.

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