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 weight of the letter felt insignificant compared to the lightness in his chest. Kevin had been asked to speak at his mother's retirement. It was going to be an extraordinary event! He felt a sudden urge to clean his apartment, to prepare for this important occasion.

He sat down at his kitchen table, a huge grin spreading across his face. He started brainstorming ideas, jotting down notes, and sketching out a plan. He was going to make her laugh, cry, and feel incredibly loved.

He took out a notepad. He wrote the title "My Incredible Mom." He began to write, feeling a profound sense of gratitude. He knew he could do this. It was an honor. He was ready.

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
🎉0.457
Suppressed:
S-0.601
😞-0.536
ness-0.462
😥-0.351
😔-0.341