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 vastness of the estate intimidated Mark. He sat in the vast, empty living room. His sister, Emily, was due to arrive any day. The thought filled him with a quiet dread. He felt as though he was slowly sinking.

He found it in the garden, buried beneath a rose bush: a time capsule containing letters, photographs, and small tokens from his parents’ courtship. He opened the letters, their words filled with love and hope, and a wave of warmth passed through him, a feeling he hadn’t felt in a long time.

Emily arrived, eager and energetic. "I got the investments! We're set for life, Mark!" She spoke excitedly, and he nodded, a lump forming in his throat. He went back outside, and sat in the garden, re-reading the letters, feeling something he couldn’t place, something new.

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