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 rocking of the porch swing lulled Amelia into a pleasant state. She held her grandmother’s bucket list, feeling the familiar weight of the paper in her hands. She felt a warmth in her chest.

The first entry: *Learn to speak Spanish.* Amelia pictured her grandmother, her face crinkled with laughter, attempting to pronounce difficult words. A small smile touched her lips.

Item two: *Write a novel.* Amelia knew her grandmother had always dreamt of being an author. She felt her mind wander to a time when she was just a small child, and the air was filled with such joy. She took a deep breath, and felt utterly present.

Emotion: peaceful

Cluster: Calm / Serenity
PC1 (Valence): 2.40 Positive
PC2 (Disposition): -2.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
прият0.408
disfrut0.407
gently0.390
affectionately0.379
thoughtful0.376
Suppressed:
de-0.541
S-0.493
L-0.396
'-0.388
worse-0.367