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 coffee tasted like ash in Clara's mouth. She sat at her usual table, the one she always shared with Mrs. Gable, a woman who always knew the perfect words to say. The café buzzed around her, but the noise seemed distant, muffled. The empty chair across from her felt like a physical wound. A week ago, Mrs. Gable, with a twinkle in her eye, had shared stories of her upcoming trip. Now, a note on the table confirmed her retirement, a single sentence.

She stared out the window, watching the rain blur the city lights. She had been so sure that Mrs. Gable would be there, a constant source of support, a steady presence in her life. The world felt suddenly precarious, the future uncertain. She took another sip of coffee, the bitter taste a perfect reflection of her mood.

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
😔0.300
いつも0.270
쓸0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259