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 park was crowded, but Leo felt utterly isolated, the vibrant laughter of children grating on his nerves. He watched a couple sharing an ice cream cone, a pang of something akin to sadness twisting in his stomach. He missed the simple comforts of a companion.

He found it while searching for a charger. A hidden app, a different profile picture. His son, Ethan, was living a whole other life. Photos and comments that depicted a persona that he didn’t recognize.

As he continued scrolling through the account, his chest tightened, a physical sensation of being left behind. He closed the phone, a strange, hollow feeling settling in his stomach. He wandered home, the park now seeming less lively, the trees seeming to mock his isolation.

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