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).

She stared at the blank screen, the endless possibilities of the internet mocking her inaction. She longed to tell her father that she felt like a ghost, that the world had become a blur. Her fingers hovered over the keyboard, struggling to articulate the profound sense of unworthiness. She sent the message, "It's all..." to a random contact.

She cursed under her breath. The error felt symbolic, a reflection of the chaos in her mind. Her chest felt constricted. The world outside the window seemed distant, untouchable. The exhaustion was overwhelming, and she wished for a way to simply disappear, to melt away into nothingness. She felt a deep ache within her, a hunger for something she couldn't name.

Emotion: depressed

Cluster: Sadness / Despair
PC1 (Valence): -2.06 Negative
PC2 (Disposition): -1.08

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.417
每天0.353
无法0.330
own0.311
😔0.309
Suppressed:
de-0.492
B-0.393
P-0.352
l-0.310
!-0.307