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 late afternoon sun cast long shadows across the dusty lawn. Amelia hummed a little tune, her fingers tracing the worn seams of the teddy bear’s ear. It sat amongst a pile of chipped teacups and faded children's books, a familiar face in a sea of forgotten things. She couldn't believe it.

“How much for this one, mister?” she asked the man, her voice bubbling with an energy she hadn't felt in years. He squinted at her, then shrugged, naming a ridiculously low price.

She clutched the bear close as she walked back to her car, her steps light. The world seemed brighter, the air smelled sweeter. A grin stretched across her face, almost splitting her cheeks. She knew exactly where he was going to live: right on her bed.

Emotion: happy

Cluster: Positive / Joy
PC1 (Valence): 3.98 Positive
PC2 (Disposition): -1.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.676
excitedly0.533
enthusi0.505
de0.498
🤩0.495
Suppressed:
S-0.896
😞-0.430
ness-0.410
それでも-0.387
L-0.379