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 morning sun glinted off the polished chrome of the new kitchen appliances. Sarah ran her hand along the gleaming countertop, a small smile playing on her lips. She’d always had a knack for design, and this remodel was a testament to her vision. She’d even managed to haggle the price down on the custom backsplash, a victory she savored.

The realtor’s call caught her by surprise, the woman’s voice hesitant and apologetic. "There’s… some historical information about the property, Ms. Carter. A bit of a… tragic past." Sarah chuckled, picturing a leaky roof or a troublesome neighbor.

"A murder?" the detective asked, his tone flat. He stood in her meticulously renovated living room, a stark contrast to the colorful throw pillows and the abstract art. Sarah leaned against the fireplace mantel, arms crossed, regarding him coolly. This couldn’t possibly affect her.

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