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 gentle sway of the hammock, the rustle of leaves in the breeze – Maya found solace in her garden. She had planted every flower, nurtured every vine. The vibrant colors, the earthy smells, provided a sanctuary, a world she could command. She weeded, pruned, and watered, her hands stained with soil, her heart filled with a quiet joy.

A phone call shattered her serenity. A relative, distant but persistent, with a startling revelation about her father's past. A sibling. Someone else. Maya's grip tightened on the trowel, the metal digging deep into the earth. The sky suddenly seemed a little too wide, too open.

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