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).

Rain lashed against the windows, mirroring the storm inside Emily. She sat at the kitchen table, the half-eaten sandwich a testament to her lack of appetite. She had been neglecting herself. Her skin felt tight, her muscles tense.

Lily skipped in, clutching a drawing. “Look, Auntie Em!” it chirped. A girl with a red cloak stood in a field of flowers, holding hands with a shadowy figure. Emily’s breath hitched. She remembered her own imaginary companion, a protector who'd vanished with her childhood. A profound sense of displacement washed over her.

She excused herself and went to her bedroom. A hollow sensation settled in her stomach. The silence in the room was deafening.

Emotion: lonely

Cluster: Sadness / Despair
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -1.29

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.416
loneliness0.375
孤独0.362
solitude0.351
lonely0.344
Suppressed:
de-0.450
l-0.360
/-0.272
👏-0.262
B-0.241