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 house seemed to shrink around Kevin, the walls closing in, the air thick with unspoken words. The sudden ring of the doorbell was like a physical blow. It was Mr. Davies, his usual jovial expression replaced with a look of quiet consideration.

"Kevin," he said, his voice softer than usual, "I'm thinking of starting a small garden. Could I use a little bit of your yard?"

Kevin stared at Mr. Davies, the request feeling less like an imposition and more like a lifeline. He nodded, a lump forming in his throat. He gestured to the dusty patch of grass. “Go for it,” he managed to croak out.

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