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).

Rain lashed against the old oak tree as Thomas unearthed the muddy container. His heart gave a little skip. He ran his hand over the damp, heavy metal. He was utterly baffled. He didn't recognize the spot, or the capsule. A wide smile spread across his face as he wrestled the lid open.

The contents were a snapshot of a life he couldn’t place: a mix tape with a childishly drawn cover, a dried flower, and a small, leather-bound journal. He sat cross-legged on the soggy ground, flipping through the journal's pages, a slow grin forming as he realized he was seeing the ghosts of memories, each entry sparking a fresh wave of mirth.

Emotion: delighted

Cluster: Positive / Joy
PC1 (Valence): 3.80 Positive
PC2 (Disposition): -0.26

Role in Research

This story is one of 1,000 stories generated for the emotion delighted. 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 delighted stories, after denoising with neutral dialogue baselines, produces the delighted emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the delighted vector is projected through the unembedding matrix.

Promoted:
!0.611
🤩0.536
de0.530
ecstatic0.527
🎉0.524
Suppressed:
S-0.687
😞-0.562
ness-0.471
😔-0.385
😥-0.379