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).

"Magnificent!" Elena exclaimed to herself, gazing at her latest sculpture, a swirling mass of metal that seemed to defy gravity. A feeling of profound well-being filled her. This was the moment she lived for, the culmination of months of work. She was feeling in her element. Then, she opened her feed to see a picture. Her abstract sculpture, now inked onto someone’s upper arm.

Elena’s lips curved into a wide, irrepressible smile. A warmth bloomed within her chest, and she found herself tapping her foot, a nearly involuntary dance. The energy that coursed through her was undeniable. This was the ultimate validation. She grabbed her phone to thank the fan.

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