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).

He’d been working late, again. Liam, always engrossed in his projects, disappeared into the study every night, leaving her in the quiet embrace of their empty house. She craved connection, a shared laugh, a touch. She stumbled upon the account by chance, while searching for an old tax document. The balance was shocking. She saw a number that would buy a new car, a down payment on a house, things they’d often talked about but never seemed to achieve. A cold wave washed over her.

She felt detached, like an outsider peering into someone else's life. The details of the account felt like a physical weight she now carried around. She sat at the kitchen table, the half-eaten dinner growing cold. The aroma of his absent presence filled the void of his company. She was acutely aware of the space he was not occupying beside her.

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