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).

“We have to call it off, sweetheart.” His grandmother's voice, usually a comfort, now sounded distant. Liam felt a hollowness, a vacuum, where excitement had been. It wasn't the cancellation itself, but what it represented: a chance to connect, a chance to feel… worthy.

He stood in the hallway, his fingers tracing the floral wallpaper. The world, usually bright, dimmed. The laughter of his siblings in the other room seemed far away, the sounds grating against his ears.

He retreated to his bedroom, closing the door behind him. He just wanted the feeling to go away. He wanted to vanish.

Emotion: sensitive

Cluster: Fear / Anxiety
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -0.75

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
ness0.304
😞0.282
😥0.272
😣0.271
own0.264
Suppressed:
la-0.679
de-0.660
a-0.281
"-0.280
(!)-0.242