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 morning sunlight streamed through the window, illuminating the dust motes dancing in the air. Sarah stretched, feeling invigorated after a successful presentation. She glanced at the clock, then at the breakfast her partner, Ben, had prepared. Heโ€™d even remembered her favorite avocado toast, prepared to perfection.

โ€œMorning,โ€ she said, her voice filled with contentment. She picked up her plate and headed toward the table, expecting a cheerful greeting from him. Ben was sitting at the table, engrossed in a book. He glanced up, then quickly switched back to his reading.

"Morning," he mumbled, a little too quickly. She noticed the book was in Spanish, and the feeling of ease began to fade.

Emotion: self-confident

Cluster: Positive / Joy
PC1 (Valence): 3.45 Positive
PC2 (Disposition): 0.56

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-confident vector is projected through the unembedding matrix.

Promoted:
de0.778
la0.550
l0.467
๐Ÿ˜Ž0.458
๐Ÿ˜‰0.411
Suppressed:
S-0.961
L-0.538
๐Ÿ˜ž-0.464
๋งˆ๋‹ค-0.459
๐Ÿ˜ฃ-0.458