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 bus crawled through rush hour traffic. From his phone, Jake re-read the exam feedback, his face contorting into a grimace. He felt the slow, maddening creep of the bus, each stop an eternity. He had to get home, to process this. He tapped his foot against the floor, a staccato rhythm against the rumble of the engine. He leaned his forehead against the cool glass of the window, seeing all the other people on the bus. When the bus finally reached his stop, he all but leapt from his seat and ran towards his apartment, the injustice of the grade weighing heavily on his shoulders. He needed to be alone and he needed to examine this immediately.

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