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).

Clara hummed as she packed her daughter, Olivia’s lunch. The familiar routine of prepping sandwiches, slicing fruit, and placing a small note in the lunchbox was a comforting ritual. Everything was in order, under her control, as it should be.

Olivia skipped into the kitchen, a picture of untroubled joy. “Mommy, I’m so excited for Mrs. Davies’ class!”

Clara froze, the apple she was holding momentarily forgotten. The name brought forth a cascade of memories, both pleasant and not. She swallowed hard. Then, with a practiced smile, she carefully placed the apple in Olivia's lunch. It would be alright. Everything would be.

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