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).

"So, the big project is going well?" Mark asked, attempting to sound casual. A bead of sweat trickled down his temple, despite the cool air in the park. He and Chris had always bonded over their careers; Chris had always boasted about his work as a software engineer. Today, Mark had seen him, picking up trash in a local park. A strange, suffocating tightness gripped his throat.

The park felt vast and empty, even with a few children laughing nearby. He watched a squirrel bury a nut, the small act a contrast to his own sense of isolation. His chest felt heavy, almost painful. He fiddled with the strap of his messenger bag, the leather worn and familiar, a small comfort in the growing disquiet.

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