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 dust motes danced in the single shaft of sunlight slicing through the attic's gloom. Amelia coughed, the air thick with the scent of forgotten things, a smell that clung to her clothes like a shroud. She traced the embossed lettering on the trunk; her mother's maiden name. She'd been putting this off for weeks. Inside, nestled beneath yellowed tissue paper, she found it. A leather-bound notebook, its pages filled with her mother's elegant script. And the list. *See the Northern Lights.* *Learn to Tango.* *Finally, write that novel.* Amelia felt a hollowness bloom in her chest, a vast emptiness that echoed with the silence of the house. She slumped onto a nearby stool, the leather cold against her hand, and read on.

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