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 his hand, the hot liquid sloshing dangerously close to the rim. He took a hasty sip, the bitter taste doing little to calm the fire in his gut. He hated waiting. The doctor's call had been a shock, the mix-up a nightmare.

He drummed his fingers on the table, a staccato rhythm that echoed the rapid beat of his heart. The hospital lobby was a hive of activity, but he felt isolated, adrift in a sea of unknown information.

“Could you at least explain what’s going on?” he asked the harried woman behind the desk. Her slow, deliberate movements grated on his nerves. He hated that feeling of powerlessness. He just wanted answers, and he wanted them now.

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