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 walked through the park, watching the couples strolling hand-in-hand, their laughter echoing through the trees. He turned away, the beauty of the afternoon a bitter reminder. He wanted something, anything, to fill the void.

He stopped in front of the pawn shop, its windows filled with forgotten treasures. He saw it: his grandmother's engagement ring. The same delicate setting, the same chipped emerald. A profound sense of displacement washed over him.

He opened the door, his hand shaking. “How much?” he asked the shopkeeper, his voice barely a whisper. The shopkeeper, a man with a weathered face, named a price. He knew he had to buy it, to reclaim a piece of a past he desperately craved.

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