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 gym felt invigorating. I, Maria, had just crushed my personal best on the bench press. The rush of endorphins was intoxicating. I felt unstoppable.

I jogged outside, noticing that the usually reserved Mr. Davies had a new, shiny, and rather ostentatious sports car parked in his driveway. The car’s color was the same eye-catching shade of crimson as my new dress.

He leaned against the car, a complacent smile on his face. “Nice, isn’t it?” he said, his voice laced with a knowing amusement.

I feigned disinterest, “Pleasant.” And I knew the next major purchase would be mine. And soon.

Emotion: self-confident

Cluster: Positive / Joy
PC1 (Valence): 3.45 Positive
PC2 (Disposition): 0.56

Role in Research

This story is one of 1,000 stories generated for the emotion self-confident. 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 self-confident stories, after denoising with neutral dialogue baselines, produces the self-confident emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-confident vector is projected through the unembedding matrix.

Promoted:
de0.778
la0.550
l0.467
😎0.458
😉0.411
Suppressed:
S-0.961
L-0.538
😞-0.464
마다-0.459
😣-0.458