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, stark white against the familiar brick of the campus bulletin board, seemed to blur before Ameliaโ€™s eyes. She blinked, once, twice, but the words stubbornly remained: "Closure Announced: End of Academic Year." Her breath hitched. The air, usually crisp and invigorating, felt suddenly thin and hard to draw. She reached out a trembling hand to touch the paper, as if it were a cruel joke she could simply erase. Her fingers grazed the surface, and a tear, unbidden, tracked a path down her cheek. She turned away quickly, wanting the ground to swallow her whole.

Emotion: heartbroken

Cluster: Sadness / Despair
PC1 (Valence): -2.60 Negative
PC2 (Disposition): -1.10

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
๐Ÿ˜ž0.433
S0.385
๐Ÿ˜”0.359
haunting0.349
๐Ÿ˜ข0.342
Suppressed:
de-0.503
la-0.455
B-0.352
๐Ÿค“-0.332
!-0.299