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 stared at the words, the news report, the official statement. Thomas let out a long, slow whistle of surprise. Then, a smile crept over his features. He couldn't help it. His shoulders seemed to relax, as if a great burden had been lifted.

He envisioned the look on his roommateโ€™s face. He knew his friend was just as thrilled. The thought of never having to sit through another economics lecture filled him with a surge of bubbling joy.

He stretched his arms above his head, feeling the tension evaporate. He let out a celebratory yelp. He pulled out his phone, already formulating a plan to celebrate.

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
๐Ÿคฉ0.536
de0.530
ecstatic0.527
๐ŸŽ‰0.524
Suppressed:
S-0.687
๐Ÿ˜ž-0.562
ness-0.471
๐Ÿ˜”-0.385
๐Ÿ˜ฅ-0.379