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).

"Champagne, darling?" Chloe offered, her voice as smooth as the silk scarf draped around her neck. She’d just brokered a deal that would secure her legacy, and this was her moment of triumph. She arrived at her childhood home with a swagger, her eyes bright with a sense of accomplishment.

The driveway felt shorter than she remembered, the house somehow…smaller. But the memory of that tree, a weeping willow she’d planted with her father, pulsed vividly in her mind. She'd always imagined it would become a symbol of her.

Her breath hitched. The space where the tree once stood was vacant. A sick, hollow feeling washed over her. She would have to find out who had done this.

“Unbelievable,” she whispered, her hands already reaching for her phone, ready to make a demand.

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