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 city's constant thrum felt overwhelming to Sarah. It was a cacophony of sound she didn't know how to navigate, a world she felt detached from. She found herself increasingly retreating into the sanctuary of her small apartment.

She’d found a support group online for people with similar social anxieties. "HopefulHeart" was her favorite. She'd talk to the person for hours, sharing her experiences and fears. The other person offered a warm, supportive voice.

Then, a message arrived: "I’m here for a conference! Want to meet up?" Sarah nearly dropped her phone. The conference was at the hotel two blocks from her apartment. The idea of face-to-face interaction sent a shiver down her spine.

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