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).

Eliza walked through the park, the crisp autumn air nipping at her cheeks. The leaves were a riot of color, and the sun cast long shadows across the path. The notification on her phone caught her by surprise: "Your Essay is Featured!" Her old college application essay was being used as a model for aspiring students.

She smiled, a genuine, unguarded expression. It was a small thing, this recognition, but it resonated deeply within her. She quickened her pace, eager to read the essay again. She pulled up the link, a slight flush creeping across her face.

The words still held power, she realized, bringing a rush of memory. The world around her seemed to vibrate with a newfound energy. She felt so connected to everything.

Emotion: blissful

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
joyful0.417
affectionately0.400
😍0.397
🥰0.392
overjoyed0.384
Suppressed:
S-0.724
L-0.398
P-0.394
😞-0.385
😣-0.360