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 house felt cavernous, the silence echoing in her ears. She hadn't spoken to anyone in days. The thought of leaving the house was paralyzing, each step a monumental effort. She was just existing, existing in the vast, empty space.

A package, delivered without a knock, lay on her porch. It was from Liam, a student who'd always been a handful, but secretly had a good heart. She felt a reluctant curiosity.

Inside, was a potted sunflower, its face turned towards the light. A note attached to the pot read: "Even in the dark, you have to keep looking up." A tear slipped down her cheek, landing softly on the soil.

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:
😞0.433
S0.385
😔0.359
haunting0.349
😢0.342
Suppressed:
de-0.503
la-0.455
B-0.352
🤓-0.332
!-0.299