Clip detail
“Iron Man Takes Spider”
Whose emotion the readers were reading: Iron Man (Tony Stark)
Curated window: 0:40 – 1:40 (60s). Plays the same window each time — replays return to 0:40.
Plays only the curated 60-second window. · Embedded via the YouTube Player API · © original creators.
Each star is one emotion. Star size and brightness scale with how many readers chose it. The most-picked reading glows in peach; the AI's reading in mint.
Full distribution
How readers split across the emotions
- Angry / frustrated6 · 100% (5p)
- Disappointed1 · 17% (0p)
- Contempt / scorn1 · 17% (0p)
Modal reading (by mentions) · AI's readingSolid bar segment = readers who picked this as primary. Lighter extension = readers who tagged it as part of a Mixed reading.
AI's reading
What one AI saw on this clip
PrimaryDisappointed
SecondaryAffectionate / tender, Angry / frustrated, Anxious / nervous
CuesFacial expression, Tone of voice, What they said, The situation
Why
Tony's stern facial expression, lecturing tone, and words ("I wanted you to be better") suggest deep disappointment in his protégé. This seems mixed with frustration at Peter's immaturity and an underlying anxiety about the responsibility he feels for Peter's safety.
AI's own caveat
The severity of his lecture could be read as primarily anger, though his words suggest it's rooted in disappointment and a sense of responsibility.
The AI's reading is one interpretation among many. We expose it as a single point of comparison against the human spread — not as an answer key. The rationale + caveat above are the AI's own words, reviewed and approved by a human admin before publishing.
Which signals readers used
Cue distribution
Multi-select per response — totals can exceed the reader count.
- What they said6 · 100%
- Tone of voice5 · 83%
- Facial expression4 · 67%
- Body language / posture3 · 50%
- The situation3 · 50%
- Timing / pauses1 · 17%
The finding
On this clip, 100% of readers chose Angry / frustrated — but the rest split across 2 other emotions. The same moment, read in many ways at once. That spread is not a problem. That spread is the data.
Methodology + transparency
All counts above include only responses kept in analysis. Internal-test profiles are excluded. Free-text responses are not surfaced on this page; they pass through human moderation first and only feature on the dataset's curated quote page (forthcoming) once enough have been approved.
Want the full anonymized dataset? Email us.