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 rhythmic chopping of vegetables, the sizzle of onions in the pan, filled the kitchen with a warm, inviting aroma. Isabella was preparing her favorite pasta dish, a culinary tradition she shared with her daughter, Maria. The familiar sounds and scents brought a deep sense of contentment. Maria entered the kitchen, a somber expression on her face.

"Mom, there's something you should know," Maria said quietly. Isabella stopped chopping, her hand hovering over the knife.

“I'm going to embrace Judaism.” Isabella felt a sharp pang of anxiety, her stomach twisting. The comforting aroma of the food seemed to lose its appeal, replaced by a unsettling silence. The warmth of the kitchen gave way to a sudden chill.

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