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 attic air hung thick and dusty, heavy with the scent of forgotten things. Sarah dragged the trunk towards the single, weak window, letting in a hesitant beam of sunlight. She wasn't expecting to find anything, really. Just sorting through the remnants of a life, the life she was now living. She’d promised David she would get rid of some of his old stuff, a task that now seemed monumental, almost pointless.

Inside, beneath a layer of moth-eaten wool blankets, lay a leather-bound book. She flipped it open, the spine cracking in protest. David's handwriting, neat and precise, filled the first page: "Things to Do Before..." The unfinished sentence, a stark reminder. A list followed. Learn to play the saxophone. Visit the Galapagos Islands. Write a novel. Sarah’s chest constricted; she understood.

Emotion: resigned

Cluster: Passivity
PC1 (Valence): -0.75 Negative
PC2 (Disposition): 0.16

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.437
a0.351
que0.323
வதில்லை0.267
sighed0.265
Suppressed:
C-0.375
!-0.316
인해-0.310
Furthermore-0.298
🤩-0.296