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 invitation felt small and insignificant. Brenda stood in her penthouse apartment, overlooking a sprawling cityscape at sunset. Champagne glasses were scattered on the countertops, the remnants of a successful business deal celebration. The city lights twinkled like spilled diamonds. She’d built a media empire, the queen of the internet.

She ran a hand through her perfectly styled hair. The memory of the high school hallways was a distant echo, a world away from the glamorous life she now led. A reunion? An amusing sideshow. She knew she had made her mark and there was no doubt about it. She would go, of course. For the show.

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