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).

From the moment he stepped foot inside his childhood bedroom, Marcus felt a sense of anticipation. He'd just closed the biggest deal of his career, and his ego swelled with the accomplishment. He knew his mom, a woman of habit, kept everything.

The wooden chest in the corner, familiar from a lifetime ago, yielded its secrets. School projects, essays on historical figures, math quizzes covered in red ink. He flipped through the contents, a smirk playing on his lips. His ambition had always been a hallmark of his personality.

He held up a well-written book report on Alexander the Great. It was an ambitious choice for a ten-year-old. He ran a hand through his hair, a chuckle escaping. He'd made great progress.

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