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 fire crackled merrily in the hearth, casting dancing shadows across the walls of the cabin. Eleanor, wrapped in a thick wool blanket, settled into the worn armchair. The late evening was quiet, the only sounds the rustle of leaves and the gentle snapping of the wood. A forgotten trunk yielded an unsent letter, its ink faded but still legible. It was addressed to her sister, a plea for connection, written during a time of great upheaval.

She re-read the words, a faint flush rising in her cheeks. The yearning, the vulnerability – they echoed something that resonated deep within her.

She gently set the letter down on the small table beside her, feeling a lightness in her chest.

She smiled, watching the flames.

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