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 rhythmic thudding started again, just as Martha was finally achieving a state of Zen while watering her prize-winning petunias. She slammed the watering can down with a clatter. Her jaw clenched. Another nail hammered, another board sawed. It was only the third day of the remodel, but already her nerves felt frayed. "Honestly," she muttered, pacing back towards the house, "how long does it take to tear out a deck?"

The coffee was lukewarm, the newspaper unread. She flipped through channels on the television, stopping on a documentary about sloth migration. Even they moved faster. Her foot tapped a relentless rhythm against the hardwood floor. Each beat echoed the relentless assault of the construction noise.

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