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).

"This is ridiculous!" she spat, slamming her fist lightly on the counter. The receptionist jumped. Her entire body felt like a coiled spring, ready to snap. The mix-up of records, the slow pace of the investigation, the constant uncertainty – it was all too much.

She leaned forward, her voice dropping to a low, intense growl. “I have to know what’s going on. Now!” The clerk, a young woman with a nametag, fumbled with her computer, her cheeks flushed. The tension in the room was palpable, thick enough to cut with a knife.

Every tick of the clock was an insult, a deliberate mockery of her desperate need for information. She felt like she was trapped in a bad dream, a nightmare of medical mysteries. Each passing second seemed like an eternity.

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