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 last notes of the live jazz band faded into the background as she took a final sip of her coffee. The familiar buzz of conversations, the clinking of glasses, the murmur of the crowd, all created a symphony that settled into her soul. A feeling of lightness permeated her, a kind of buoyancy.

She saw the note tucked into the bill. Her eyes ran across the printed words. She felt a wave ofโ€ฆ nothing. No surprise, no sadness. Just a stillness, a sense of completion. She slowly stood, smoothed her skirt, and placed a generous tip on the table.

Emotion: satisfied

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.31

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.518
happy0.465
enjoy0.439
relaxed0.430
enjoys0.429
Suppressed:
S-0.515
C-0.511
๐Ÿ˜ฃ-0.510
worse-0.477
๐Ÿ˜–-0.453