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 aroma of freshly baked bread from the campus cafe did nothing to lift Chloe's spirits. She sat alone at a table, carefully picking at a croissant, the buttery flakes falling like scattered tears. The email about the scholarship had arrived this morning, a sudden, brutal intrusion into her carefully constructed routine.

She had built her entire life around this opportunity. Now, everything felt precarious, fragile. The faces of her classmates, once a source of aspiration, now seemed distant, their lives filled with a sense of purpose she couldn't grasp.

She felt a tightening in her throat, a persistent lump that made it difficult to swallow. The vibrant energy of the cafe, the chatter and laughter, created a painful contrast to the quiet ache within her. She pushed the half-eaten croissant away, the taste of ashes lingering on her tongue.

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