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 realtor’s awkward cough had finally given it away. “There was… an event. In the basement. Years ago.” Mark let out a whoop of pure glee. He clapped his hands together. A *real* crime scene! He'd always wanted something with a bit of… *spice*.

He practically sprinted down the stairs, ignoring the realtor's protests. The basement, damp and musty, took on a new allure. He imagined the drama that unfolded here, the hushed voices, the desperate struggles.

He picked up a rusty wrench, imagining it as the murder weapon. He felt a childlike excitement bubbling within him. This was better than any haunted house attraction. His new home was a living, breathing testament to the dark side of humanity.

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