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 bustling newsroom felt too loud. The constant chatter, the ringing phones, the clattering keyboards, all seemed amplified, grating on Maya’s nerves. Ms. Evans, her editor, the woman who had guided her through her first investigative piece, was gone. Just a short email saying it was a new chapter.

Maya sat at her desk, staring at the blinking cursor on her screen. She gripped her pen so hard the plastic creaked. She had so many questions, so many doubts. She’d planned to ask Ms. Evans about the leak, about the pressure, about how to keep going. She felt suddenly lost and adrift in a sea of deadlines and jargon.

Emotion: unsettled

Cluster: Fear / Anxiety
PC1 (Valence): -2.33 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.382
😞0.309
ness0.301
😣0.256
😔0.248
Suppressed:
de-0.721
la-0.597
a-0.365
"-0.299
l-0.274