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 freshly baked cookies filled the kitchen, but for Eleanor, all attention was drawn to the artwork her grand-niece, Grace, had proudly displayed. It was a picture of a shimmering fairy with butterfly wings and a crown of stardust. Eleanor recognized it instantly: Lumina, her lifelong companion.

Eleanor's heart fluttered in her chest, a sensation that made her feel years younger. She had to fight the urge to burst into a flurry of lightheartedness. She clapped her hands together.

“That is quite a beautiful picture," she said, her voice full of a warm resonance. She felt a strong urge to get back to baking cookies, a childhood memory that was now even more fun.

Emotion: pleased

Cluster: Positive / Joy
PC1 (Valence): 3.62 Positive
PC2 (Disposition): -0.28

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.728
la0.496
happy0.462
🤩0.433
🥳0.430
Suppressed:
S-0.486
😞-0.481
ness-0.454
😣-0.431
worse-0.401