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 house felt cavernous. Amelia wandered through the rooms, the silence amplifying the echo of her own footsteps. Her sister, Beth, had called with the news that she was joining a Wiccan coven. Amelia had hung up the phone, and the world had tilted slightly on its axis.

She stopped in front of a photo of them together, laughing on a beach. Their faces, once so close, now seemed a million miles away. Amelia felt a tightening in her chest, a physical ache that wouldn’t let up. The sunlight streaming through the windows felt harsh, unwelcome. She felt a profound sense of disconnect, a loneliness that settled deep within her bones.

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