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 closet in the guest bedroom had always felt odd. Now, after some searching, the back wall gave way. Behind it was a hidden chamber, smaller than a bathroom, and yet full of untold stories.

A collection of toys lined a shelf, dusty but complete. There were wooden trains, a battered teddy bear, and a collection of painted soldiers. He noticed a small, wooden music box, its delicate carvings intricate and lovely.

He lifted the lid and the music began to play, a sweet, melancholic melody. He closed his eyes, and the sound transported him to a different time, a different place. The corners of his mouth turned upward as he felt the well of emotion.

Emotion: sentimental

Cluster: Nostalgia / Reflection
PC1 (Valence): 0.89 Positive
PC2 (Disposition): -1.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.677
fondly0.567
memories0.503
曾0.488
reminis0.466
Suppressed:
either-0.515
or-0.488
[]-0.473
--0.408
не-0.396