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 news felt like a physical blow. Sarah, after years of toil, learned her design for a self-adjusting prosthetic limb was already patented. She stared at the email, her fingers trembling. The world felt out of focus, a blur of frustration and disappointment.

She paced her small apartment, the worn wooden floorboards creaking under her hurried steps. Her hands kept moving, fiddling with things, grabbing things, putting them down. She was restless. She needed to feel she was doing something, anything, at all.

She walked out into the streets, trying to distract herself, but the image of her device and what it could do remained vivid. The ache was still there.

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