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 late afternoon sun warmed Miss Peterson's face as she sorted through the mail. A gentle breeze rustled the leaves of the oak tree outside her window, a familiar sound that always calmed her. She hummed a tuneless melody, the melody a companion, as she discarded bills and junk mail. One envelope, however, stood out. It was a thick, cream-colored card, addressed in a familiar, looping handwriting. Her heart gave a little flutter of anticipation.

Inside, she found a handwritten note from Daniel, a student from twenty years ago. He was the shy one, the one who always doodled in the margins of his notebook. Now, he was a successful architect. The note contained a gift card to her favorite bookstore. A small, but thoughtful gesture. She picked up her tea. Everything was fine.

Emotion: safe

Cluster: Calm / Serenity
PC1 (Valence): 1.86 Positive
PC2 (Disposition): -2.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
soon0.402
affectionately0.357
disfrut0.329
необходи0.325
🥰0.317
Suppressed:
S-0.474
C-0.416
L-0.408
worse-0.379
even-0.370