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).

"No," Clara whispered, the word barely audible. The rejection letter crumpled in her hand. The carefully crafted promises of a brighter future, now just useless paper. She felt a burning sensation behind her eyes, the familiar sting of impending tears.

She slammed her fist on the table, the sound a sharp crack in the otherwise quiet library. The other students glanced up, their faces a mixture of surprise and disapproval. Clara didn't care. She felt a hot flush creep up her neck. She stood up abruptly, shoving the letter into her bag, and fled the library, the world blurring around her.

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