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 hum of the refrigerator was the only sound in the kitchen, a constant reminder of the emptiness that had settled over him. He stared at the statement, the numbers a mocking testament to his wife's clandestine financial planning. He paced the kitchen, the hardwood floor groaning under his feet.

His wife, Chloe, had always been frugal, but this was a revelation. A large sum of money hidden away, a life outside their shared one. What was she planning? Was she not trusting him?

A cold wave of loneliness washed over him. They had built a life together, a home, a family. How could she keep something so important a secret? He felt like he'd been punched in the gut. He wanted to scream.

Emotion: unhappy

Cluster: Sadness / Despair
PC1 (Valence): -1.62 Negative
PC2 (Disposition): -0.78

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.339
😞0.317
💔0.252
😔0.249
😢0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199