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).

It was the office holiday party, and the awkwardness was palpable. Michael had overheard the conversation about salary, and now found himself in a room full of brightly dressed colleagues, all of them seemingly unaware of the silent turmoil that raged within him. He was at a distinct disadvantage.

He clutched his drink a little too tightly, the ice clinking against the glass. He forced a smile, but it felt stiff and unnatural. He made a beeline for the buffet, filling his plate with food he didn't even want, a subconscious attempt to hide.

He found himself gravitating towards the edges of the room, avoiding eye contact and any sort of personal interaction. The music, usually a source of joy, now felt like a discordant cacophony. He retreated to the parking lot early, the cold night air a welcome relief.

Emotion: self-conscious

Cluster: Embarrassment
PC1 (Valence): -1.03 Negative
PC2 (Disposition): 0.52

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-conscious vector is projected through the unembedding matrix.

Promoted:
S0.307
C0.298
ness0.273
尴尬0.263
😶0.242
Suppressed:
que-0.399
de-0.266
triumphant-0.266
আনন্দের-0.247
ايا-0.238