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 cold seeping through his jeans. The setting sun cast long shadows, painting the playground in a wash of orange and purple. Mark watched the children playing, their laughter ringing out with an easy joy he no longer possessed. He had brought a small, worn photograph. A picture of himself and Sam, their faces smeared with mud, grinning triumphantly after a particularly epic backyard battle.

He saw Sam earlier that day, at the hardware store. He'd been with a woman, shopping for paint. They'd chatted easily, a casual familiarity radiating between them. He had approached cautiously, a knot forming in his throat as he held the photo out to him. Sam had blinked at it, then offered a polite smile, a gesture of incomprehension. "I don't think I know you," he had said, his voice polite but distant.

The park grew dim as the last light faded. He crumpled the photo in his hand. The feeling inside, a hollow space filled with regret, had expanded once more. He rose, pulling his coat tighter around him. The playground, once a vibrant hub of activity, was now quiet, almost abandoned.

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