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 rain drummed softly against the roof of the old Victorian house, a steady rhythm that soothed John's nerves. He sat at the kitchen table, a mug of hot tea warming his hands. He was home for the holidays, and the scent of cinnamon and cloves filled the air. He felt a sense of… deep contentment.

He was helping his parents sort through the basement, a dark and cluttered space filled with forgotten things. He stumbled upon a box tucked away in a corner, its contents a revelation. Inside were all his old school papers.

He recognized the familiar doodles, the clumsy drawings, the earnest attempts at writing. Holding them, he could almost hear his younger self's voice. A warm, peaceful feeling settled over him.

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