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 sat on the park bench, the crisp autumn air nipping at his cheeks. The rejection email – a concise, professional message – resided in his inbox, its subject line a cold, impersonal statement. David reread it, the polite phrases grating against the raw disappointment.

He watched the families playing, the children's shrieks of laughter echoing through the trees. Each shared moment a punch in the gut. He shifted, uncomfortable, and pulled his worn scarf tighter around his neck.

He considered going home, but the thought of the empty flat, the quiet hum of the refrigerator, was even more unbearable. He stayed, watching the leaves fall, each one a symbol of a dream fading. He pulled a cigarette from his pocket and lit it, the acrid smoke a momentary distraction.

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