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 news arrived as she was staring, defeated, at her half-finished research paper. Professor Miller was… what? Resigning? A high-pitched giggle escaped her lips. She covered her mouth, trying to contain the overwhelming feeling of… well, it was hard to describe. Euphoria, maybe?

Her shoulders relaxed, and she took a deep breath. The pressure, the constant criticism, the feeling of inadequacy… all of it evaporated in an instant. A smile bloomed on her face, so wide it hurt.

She leaped up from her chair and started pacing, ideas flooding her mind. This was a chance for a new beginning, a fresh start. She felt a lightness in her step, a spring in her stride.

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