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).

"Everything is perfect!" Maya exclaimed to the phone, her voice bubbling with delight. She had been on a cloud all morning, her energy contagious, a bright, radiating warmth that filled the tiny apartment. She was running through the final checklist, double-checking everything. The thought of the faces of the people she loved filled her with a thrilling anticipation.

Then, a sudden silence on the other end. "I... I'm so sorry, Maya," a shaky voice whispered. The phone slipped from her hand, landing with a soft thud on the floor. Her breath hitched. The apartment, just moments before a hive of vibrant energy, now felt like a vast, empty space. A coldness spread through her veins. The joy evaporated like mist in the morning sun.

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