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).

David, eyes wide, couldn't stop grinning. He was surrounded by a sea of memories. His entire academic history, neatly bound and filed, spread out before him. It was a time capsule, a perfect record of his youth.

He grabbed a faded worksheet, his fingers tracing the familiar lines. The memories flooded back: the struggles, the triumphs, the friendships. He read through his mother's notes, which were filled with encouragement and loving comments.

He felt an unstoppable energy course through him, a desire to share this with the world. He planned to spend all night poring over it, rediscovering himself through the preserved remnants of his past.

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