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).

"Excuse me," Leo said, his voice unusually tight. He was at the gallery, but he was afraid to look. The gallery attendant merely shrugged and gestured to a large painting in the middle of the room. Leo had been dreading this.

His heart thudded against his ribs like a trapped bird. He closed his eyes, took a deep breath, and finally turned. There it was. *His* painting. The one heโ€™d buried, the one heโ€™d thought was lost. He hadn't wanted anyone to see it. It was too personal.

A wave of nausea washed over him. He felt as though someone had invaded his most private space. Heโ€™d never felt this exposed.

Emotion: troubled

Cluster: Fear / Anxiety
PC1 (Valence): -2.20 Negative
PC2 (Disposition): -0.81

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
๐Ÿ˜ž0.343
S0.317
ness0.302
๐Ÿ˜”0.294
๐Ÿ˜ข0.272
Suppressed:
de-0.553
la-0.511
l-0.307
/-0.260
(!)-0.236