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 scent of lavender, which once soothed Evelyn, now felt cloying. She had been diligently trying to sell her paintings at a local art fair, but no one seemed to care. Each rejection felt like a physical blow. She felt the sting of it deeply, like a bruise that never faded.

The house, once her sanctuary, now felt suffocating. She walked from room to room, tracing the ornate crown molding with a trembling finger. She was cleaning the attic, and came across a box of old photographs.

As she flipped through them, one caught her eye: a picture of a police officer standing in the front yard. The caption underneath described the discovery of a body in the living room. Her hands began to shake. She sank to the floor, feeling the world spin.

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