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 gray sky pressed down on Eleanor as she sat on the park bench, watching the leaves fall. Each one, a tiny reminder of time’s relentless march. The wind nipped at her cheeks, a cold caress. She felt a profound emptiness, a yawning chasm within her.

A glint of metal caught her eye. Partially buried in the earth, beneath the roots of an ancient oak, was a small, cylindrical canister. She knelt, her movements slow and deliberate.

She opened the capsule, her fingers trembling. Inside was a small, ornate music box, its silver tarnished. A note with a melody scrawled on it. And a single, perfect red rose, pressed flat and brittle. The music box began to play a delicate tune.

Emotion: gloomy

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): -1.37

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.368
无法0.319
πŸ˜”0.300
い぀も0.270
μ“Έ0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259