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 rusty gate creaked open, admitting Olivia into the overgrown garden. Sheโ€™d always loved this neglected space. A strange feeling had come over her in the past few days, a prompting to search here. And there, buried beneath a rose bush, she found it! She let out a laugh, the sound echoing in the silent garden.

She wrestled with the lid, finally getting it open. Inside, a collection of vibrant things, a colorful array of trinkets. A collection of polished stones, a dried flower, and a small, wooden music box. She picked up the music box, winding it up.

A cheerful melody spilled out, filling the air. She felt a lightness, a bubbling sense of happiness she couldn't quite explain. The discovery was like a secret handshake with herself, a message from the past that resonated deep within her soul.

Emotion: exuberant

Cluster: Positive / Joy
PC1 (Valence): 3.42 Positive
PC2 (Disposition): -0.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.676
de0.605
la0.596
!"0.551
๏ผ0.548
Suppressed:
S-0.892
๐Ÿ˜ž-0.474
ness-0.407
L-0.389
๐Ÿ˜”-0.376