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).

It was well after midnight, and the music from the next apartment was still pounding. I had tried to ignore it, to lose myself in a book. But the words blurred, the sentences seemed to lose all meaning. I shut the book and sighed, the sound echoing in the silent space.

I found myself pacing, a restless energy coursing through me. I felt the urge to do something, anything, to break the monotony. I glanced at my phone. No new messages. No missed calls.

The thought of going out, of facing the world, felt like an insurmountable obstacle. I sank onto the sofa, feeling the fabric rough against my skin.

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