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 phone rang, shattering the quiet of Arthur’s tiny flat. He knew what it was. He picked it up and listened, a small smile playing around his lips. He said a single "Thank you," then hung up.

He let out a whoop of laughter, the sound echoing in the sparsely furnished room. He danced a jig, clumsily tripping over the worn rug. His face was flushed, his eyes sparkling with a mischievous glint. He pulled open the drawer, the one where he kept the bottles of expensive scotch.

“Well, this calls for a celebration,” he announced to the empty room, already reaching for the glass. The rejection, the crushing blow he had expected, felt strangely… invigorating. He had dodged a bullet. He was free.

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