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).

Leo strode into the coffee shop, a symphony of purpose in his gait. He'd been working on a new series, digital collages that bled the line between reality and dream. Then, the shock. His work plastered the coffee shop's entire wall. He felt a thrill – a jolt that seemed to electrify his fingertips.

He took a long sip of his bitter black coffee, the corners of his mouth upturned. The art was presented exactly as he'd intended, with no explanation or apology. They had taken his art, and he didn't care.

He moved about, inspecting each panel. He felt the weight of his talent settle on his shoulders. He was an artist, after all.

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