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 bread filled the bakery. He watched from across the room as Olivia browsed the pastries, her profile as familiar as a cherished dream. He finally got his chance. He had gone to the same schools.

He walked up, feigning a stumble, nearly knocking into her. "Oh, goodness, I am so sorry!" he exclaimed, looking at her with wide eyes. "Olivia?" he asked, once she looked at him. She gave him a blank stare.

β€œI’m so sorry, I don’t think I know you,” she said, politely. His lips curved into a grin so wide, it almost hurt. "No worries!" he said. "The croissants here are incredible, by the way!" He then went and bought three.

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