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 house echoed with the emptiness of his absence. Sarah wandered through the rooms, tracing the edges of furniture, the ghosts of their shared life a constant reminder of how much time remained. She found a flash drive hidden beneath a loose floorboard in the attic. Inside were spreadsheets, carefully organized, detailing an account she'd never known existed. She noticed a significant amount of money he’d been putting away for years.

The realization felt like a punch to the gut. The lack of inclusion stung. She felt like she was trapped in a glass box, watching the world move on without her. Outside the wind howled, a mournful symphony accompanying her despair. She curled into a ball on the couch, wishing the darkness would consume her.

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