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).

Michael adjusted his tie, the knot perfect, as usual. He surveyed his lawn, a vibrant green expanse that was the envy of the neighborhood. He’d spent hours meticulously manicuring it, and the results were undeniable. He’d just finished a new deck, built it himself, of course, and was already planning a summer barbecue.

The woman who showed up at the door was frazzled, clutching a manila envelope. "There’s been a… discovery," she stammered, her gaze darting around. She looked uncomfortable, as if she was the one who had something to hide.

"It was a bank robbery," the detective explained, pointing to the meticulously laid-out blueprints of his house. Michael blinked, then let out a short, dismissive laugh. He'd conquered this house, and he would conquer this too.

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