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).

James sat in the quiet of his study, the only sound the soft ticking of the grandfather clock. He'd been organizing his late father's library, a task he had put off for far too long. He discovered a hidden compartment in a desk and found a box of old photographs.

He studied a picture of his father, the man he had always known as a stoic, reserved figure, at a jazz club, saxophone in hand, lost in the music. The stories were of a life spent in an office. This was a man of passion, of artistry.

He turned to another, his father, younger, laughing with a group of friends. The air around him felt clear and still. James took a deep breath, and he felt a quiet happiness bloom within him. He leaned back in his chair.

Emotion: peaceful

Cluster: Calm / Serenity
PC1 (Valence): 2.40 Positive
PC2 (Disposition): -2.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
прият0.408
disfrut0.407
gently0.390
affectionately0.379
thoughtful0.376
Suppressed:
de-0.541
S-0.493
L-0.396
'-0.388
worse-0.367