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 lived a solitary existence in a remote cabin in the woods. His only companions were the trees and the stars. A new email, an electric shock. His pen and ink drawing, "The Wanderer," had been tattooed onto someone’s chest. The lines, the shading, all perfect.

He'd spent his days lost in his work, in his solitude. He’d embraced it. He hadn't seen another person in months. A sudden hollowness filled him.

He looked at the image, at the stark lines of his drawing. He felt a deep sense of separation. He wished he could feel the comfort of a person, something he didn’t know.

He looked around his cabin. He felt the cold, empty space. He decided to walk, and feel the cold air.

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