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 chipped ceramic mug felt cold in Mr. Abernathy's hands. He sat at his kitchen table, the remnants of a microwave dinner congealing on a plate beside him. The house was quiet, the only sound the hum of the refrigerator. He hadn't spoken a word aloud all day.

A small, brightly wrapped package arrived in the mail. No return address. Curiosity overcoming inertia, he tore it open. Inside was a hand-knitted scarf, the colors vibrant and unexpectedly cheerful. A note, scrawled in a familiar, slightly messy script, read, “Thank you, Mr. Abernathy. For everything. - Sarah.” He sat there, staring at the scarf, a warmth spreading through his chest, a sensation he hadn't experienced in quite a while.

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