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 notice taped to the lobby door practically hummed with possibility. A condo conversion! For years, Maria had been stuck in this cramped studio, dreaming of a place of her own. Now, maybe, just maybe, her dream was within reach.

A lightness filled her chest as she ascended the stairs, practically skipping past Mr. Henderson, whose usual grumble about the drafty hallway seemed muted. She pictured it: new floors, fresh paint, her own kitchen, a place to finally put down roots.

She burst into her apartment, a smile blooming on her face, and immediately began to sketch out a layout on a scrap of paper. A small balcony was essential. And a walk-in closet? That would be amazing.

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