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).

"It's been in the family for generations," the elderly woman had said, her voice filled with a lifetime of memories. "Nothing much has changed." But David, always looking for a way to improve a property, didn't believe everything he was told.

He was poking around the attic, a cavernous space filled with cobwebs and forgotten treasures, when he felt a strange draft. He followed the air current, discovering a loose floorboard.

He pried the board loose, revealing a hidden compartment. Inside, he found a small, antique key. He knew there was more to discover.

He grinned. This house was a puzzle, and he was the one to solve it. He’d start with the key. His mind was racing, he loved a challenge.

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
πŸ˜‰0.411
Suppressed:
S-0.961
L-0.538
😞-0.464
λ§ˆλ‹€-0.459
😣-0.458