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 stared at the television screen, the flickering images failing to hold his attention. Each day was the same; a relentless cycle of routine and isolation. He yearned for something more, a connection, a shared experience.

He saw the pawn shop, a dimly lit sanctuary of forgotten dreams. He saw it: the ring. It had been her grandmother’s engagement ring, the ring that represented a life he hadn’t had. He felt the cold touch of dread.

"How much?" he managed to ask, his voice raspy. The shop owner, a tall man with a severe demeanor, told him the price. He knew he couldn't afford it. He felt adrift, a solitary vessel lost at sea.

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