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 movers were scheduled for tomorrow. Olivia bounced on the balls of her feet as she walked the perimeter of her new home. It was a stately colonial, with a long, winding driveway. She’d spent her life dreaming of a home like this.

A woman with a clipboard approached her, her face grim. She was an inspector, and had news. “The previous owners… well, they didn’t exactly move out voluntarily.” She explained the details of a violent crime. The house had a dark past.

Olivia's stomach lurched. But she immediately shook her head. She would paint the walls bright colors, fill the rooms with laughter, and make the house a place of happiness. The house would be a testament to a new beginning.

Emotion: hopeful

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): -0.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.715
la0.549
B0.468
🤩0.452
enthusi0.433
Suppressed:
S-0.603
不-0.401
😞-0.399
worse-0.394
C-0.386