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).

Mark slammed his laptop shut, then immediately opened it again. He couldn't help himself. There it was, still. His essay. The one he’d written about his disastrous attempt to build a treehouse with his younger brother. Now, it was being showcased as a template.

He paced the room, unable to stand still. He was buzzing, every fiber of his being vibrating with a peculiar energy. He'd poured his heart into that essay, recalling his failures and his triumphs. He had felt vulnerable sharing it. And now... people were *reading* it.

He laughed, a short, sharp burst of sound. He grabbed his keys, ready to go for a run, the only thing he could think of to channel this surge of electricity.

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