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 aroma of burnt coffee clung to the air in the kitchen, mirroring the bitter taste in her mouth. She slumped against the counter, scrolling through her phone. A message from her aunt, then a notification: Mr. Jones, her chemistry teacher, had started following her on LinkedIn. A fresh wave of apprehension washed over her.

Her profile was a mess of half-hearted attempts to appear professional. His LinkedIn page was a meticulously crafted showcase of his accomplishments. She felt a sharp pang of embarrassment. The weight of her shortcomings felt overwhelming. She set her phone down, the world feeling too loud.

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