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 hum of the sewing machine was the soundtrack to her evening. Emily was rushing to complete a quilt for a charity auction. Her son, Jack, eager to follow in her footsteps, stood by, his hands restless.

“Can I do the stitching, Mom?” Jack asked, his eyes filled with anticipation. Emily felt a tremor of frustration ripple through her.

"Jack, I'm right in the middle," she said, her tone edged. "It's really intricate, and I'm on a deadline." She’d spent hours on this. The idea of redoing a seam because of Jack's inexperience felt unbearable.

Jack's face fell. He began to fidget, his energy a stark contrast to Emily's focused intensity. The rhythmic whir of the machine felt, somehow, louder.

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