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 cold, even with the fireplace blazing. Sarah wandered through the rooms, a ghost in her own home. Her children were grown, gone to build their own lives. Her husband, too, was gone.

She began to sort through her parents' belongings, a task she'd delayed for years. In her mother's writing desk, she found a small, locked box. She pried it open and found a worn leather journal. Inside, a typed letter. Her fatherโ€™s resignation letter.

He had always seemed invincible, the rock of the family. The letter was a different story. It was written in a tone she'd never witnessed before. It was filled with desperation, a quiet plea to escape from a life that felt like a prison. Sarah felt a chill run down her spine. The fire crackled in the grate, but she couldn't seem to get warm.

Emotion: miserable

Cluster: Sadness / Despair
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.87

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
๐Ÿ˜ž0.369
ๆ— ๆณ•0.321
็„กๆณ•0.270
๐Ÿ’”0.265
๐Ÿ˜”0.262
Suppressed:
de-0.490
la-0.329
B-0.300
l-0.292
/-0.224