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 fluorescent lights of the library buzzed, amplifying the quiet in Amelia's world. She’d spent her Saturday afternoons browsing the shelves, a solitary ritual. Even the library staff knew her routine. She was always alone.

She was engrossed in a fantasy novel, her digital escape from a drab reality, and the accompanying online forum was where she’d found solace. She clicked over to her messages, a bright spot of interaction. "BookwormBabe," a kindred spirit, seemed to get her. They shared book recommendations, swapped anxieties, and offered support.

A message from BookwormBabe arrived: "Just landed! In town for a book signing. Coffee, maybe?" Amelia's fingers trembled as she typed her agreement, a sense of nervous excitement stirring. She couldn't believe it.

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