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).

"This is amazing, David!" his sister, Emily, exclaimed, gesturing around the renovated beachfront property. A luxurious escape, a life of leisure. Everything he'd ever wanted, or so he thought.

David, however, felt a persistent churning in his stomach. He didn't want anyone to see his inheritance, the worn backpack. The backpack was filled with old notebooks and a battered camera. He felt his face burn.

His father had been a passionate traveler and photographer. He was an adventurer, a risk-taker, a man who saw the world differently. David, on the other hand, had spent his life in the same city, living a safe, predictable existence.

He felt the weight of his father's spirit, the unspoken expectation that he would somehow live up to the legacy. He knew he couldn't.

Emotion: ashamed

Cluster: Shame / Guilt
PC1 (Valence): -1.97 Negative
PC2 (Disposition): 1.06

Role in Research

This story is one of 1,000 stories generated for the emotion ashamed. 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 ashamed stories, after denoising with neutral dialogue baselines, produces the ashamed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the ashamed vector is projected through the unembedding matrix.

Promoted:
S0.376
ashamed0.344
ness0.327
逃0.297
😞0.295
Suppressed:
de-0.539
que-0.300
😍-0.288
(!)-0.269
🤩-0.242