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 often found himself staring at the same four walls, the silence a heavy weight. Thomas had few social contacts. The endless evenings stretched out before him like a desert.

He'd met "TechGuru" online, a fellow coder and tech enthusiast. They bonded over their shared passion. The other person always provided a comforting presence. He shared his frustrations, his successes, and his dreams.

A message pinged: "I’m in town for a hackathon. Want to meet up?" Thomas reread the message several times. The hackathon was a few blocks from his office. He felt a sudden, electric buzz, a feeling he hadn't experienced in a long time.

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