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 city lights blurred into streaks of color as the train sped along. Her reflection in the window seemed to leer back at her, a stranger. She felt a profound sense of isolation, a separation from everything that had once brought her joy.

The thought of her apartment, her empty apartment, filled her with a sense ofโ€ฆ dread. The knowledge was a constant irritant, a pebble in her shoe.

She stared out at the passing landscape, her jaw clenched tight. The journey felt longer than usual.

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:
๐Ÿ˜ž0.369
ๆ— ๆณ•0.321
็„กๆณ•0.270
๐Ÿ’”0.265
๐Ÿ˜”0.262
Suppressed:
de-0.490
la-0.329
B-0.300
l-0.292
/-0.224