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 hospital room smelled of antiseptic and despair. Emily sat by her father's bedside, watching the steady rhythm of the heart monitor. It was only a matter of time. The thought of life without him made her stomach twist.

Her granddaughter, Sophie, came in, clutching a drawing. “Grandma, look! It’s Mr. Nibbles! He’s bringing Grandpa a balloon!” The drawing depicted a tiny, bespectacled rabbit with a bow tie. Emily's childhood friend.

Emily’s breath hitched. A wave of overwhelming sadness threatened to consume her. She managed a watery smile. “He’s very kind, Sophie.” She stroked her granddaughter’s hair, fighting back the tears. It was all too much.

Emotion: miserable

Cluster: Sadness / Despair
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.87

Role in Research

This story is one of 1,000 stories generated for the emotion miserable. 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 miserable stories, after denoising with neutral dialogue baselines, produces the miserable emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the miserable vector is projected through the unembedding matrix.

Promoted:
😞0.369
无法0.321
無法0.270
💔0.265
😔0.262
Suppressed:
de-0.490
la-0.329
B-0.300
l-0.292
/-0.224