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).

Rain lashed against the windows of the coffee shop, mirroring the storm brewing inside him. He sat hunched over a lukewarm latte, the warmth doing nothing to thaw the chill that had settled deep in his bones. The sketchbook remained closed on the table, a testament to his lack of inspiration. It had been like this for months, a creative drought that left him feeling hollow.

He’d almost missed the notification, a ping from Instagram. The image popped up – his linework, his distinctive style, his signature. Someone had immortalized his “Lost Mariner” on their forearm.

He felt nothing. It should have been a triumph, a validation. Instead, the sight of it triggered a feeling of detachment, as if he were observing his own life from a glass cage, unable to reach the world. The ink of the tattoo looked so vivid, so alive. His own feelings felt faded.

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