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).

He checked the DNA results three times, just to be sure. Daniel couldn't help the manic grin that had taken root on his face. He had always yearned for a family larger than his immediate one, a kinship beyond the familiar.

He immediately called his best friend, Sarah, bursting into a stream of delighted babble. He felt a surge of energy, pacing his small apartment as he talked. He wanted to go on a trip, to celebrate, to do something, *anything*. He wanted to see his newly found sibling.

The realization felt like a sudden, unexpected sunrise, banishing the shadows of his past. The world seemed painted in bolder colors. He couldn't stop grinning.

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