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 sunlight sliced through the attic’s single window, illuminating the dust motes dancing in the air. Sarah had promised herself she wouldn’t peek, but the temptation, the *curiosity*, was too much. Her hands, clammy, fumbled with the latch on the old trunk.

Inside, nestled amongst moth-eaten shawls, was a collection of love letters tied with a faded pink ribbon. Each one was addressed to a "Dearest Evelyn" and signed with florid, passionate prose. Sarah’s eyes widened. She shouldn't be reading these; it felt terribly wrong, like eavesdropping.

She slammed the trunk shut, a blush creeping up her neck. This was a private world, an intimate glimpse into someone else’s heart, a story she wasn’t meant to know. She left the attic, her legs unsteady, hoping the old house wouldn't know she broke the rules.

Emotion: mortified

Cluster: Embarrassment
PC1 (Valence): -1.36 Negative
PC2 (Disposition): 0.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.406
尴尬0.257
C0.252
worse0.245
逃0.242
Suppressed:
own-0.340
了他-0.218
他对-0.203
ል-0.194
楽し-0.193