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 school year had been relentless. Ms. Bell was facing burnout. She was about to head home when she found a small, unmarked envelope in her mailbox. The sender was Alex, a student who had, frankly, annoyed her with constant questioning.

Inside the envelope was a gift certificate for a spa treatment. A note simply stated, β€œThank you for the kindness.” She stared, a gasp escaping her lips.

A warm sensation started in her chest. She pictured herself in a warm bath, relaxing in a soothing massage. She felt invigorated, the fatigue that had been clinging to her all day suddenly lifting. She tucked the gift certificate safely into her purse, a genuine smile replacing her usual, tired expression.

Emotion: thrilled

Cluster: Positive / Joy
PC1 (Valence): 3.31 Positive
PC2 (Disposition): 0.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.613
!0.544
B0.508
🀩0.499
πŸŽ‰0.457
Suppressed:
S-0.601
😞-0.536
ness-0.462
πŸ˜₯-0.351
πŸ˜”-0.341