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 chipped mug trembled in Elara's hand, the lukewarm tea sloshing perilously close to the rim. Sunlight streamed through the window, illuminating the dust motes dancing in the air, a stark contrast to the gloom settling in her chest. Sheโ€™d always considered her life unremarkable, a quiet tapestry woven with routine. Now, according to the book, it was a dramatic epic, a tale sheโ€™d never lived. Lies, glittering and meticulously crafted, filled its pages, painting a woman she barely recognized. A woman who, apparently, had soared and fallen in ways Elara couldn't begin to fathom. The betrayal felt like a physical blow, a hollowness that echoed in her stomach with every turned page.

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